[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EPKY7P8ABF1WCZFNQZQMVF":3,"skill-same:01M7EPKY7P8ABF1WCZFNQZQMVF":110},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7EPKY7P8ABF1WCZFNQZQMVF","run-card",null,"Write a RUN-CARD before touching a system you did not build. Use whenever work is about to run against a real host, a production database, someone else's data, a backup, a log, or any environment where a mistake is expensive or a false conclusion could ship — and especially when the person at the keyboard is not the person who wrote the steps. Triggers on \"write a run card\", \"card this\", \"no card no run\", \"how do I run this safely\", \"sweep the logs for X\", \"check whether Y ever happened\", \"is that host clean\", \"let's get on the box and look\", \"walk me through this\", \"what would I paste\", \"can a volunteer do this\". Also use when a run just finished and the results need reading in the right order, or when someone is about to report a CLEAN result from a sweep. This is not a checklist generator and not a devops runbook tool — it is a discipline for producing one paste-ready, auditable artifact that a careful stranger could run without you in the room.","inputloop\u002Fgarden","inputloop","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F339507215?v=4","01M7ENYT15EMVBAV30YXPQDYE2","Inputloop","01M7ENYT1SM9WM5PSMQDC9PE2G",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: run-card\ndescription: Write a RUN-CARD before touching a system you did not build. Use whenever work is about to run against a real host, a production database, someone else's data, a backup, a log, or any environment where a mistake is expensive or a false conclusion could ship — and especially when the person at the keyboard is not the person who wrote the steps. Triggers on \"write a run card\", \"card this\", \"no card no run\", \"how do I run this safely\", \"sweep the logs for X\", \"check whether Y ever happened\", \"is that host clean\", \"let's get on the box and look\", \"walk me through this\", \"what would I paste\", \"can a volunteer do this\". Also use when a run just finished and the results need reading in the right order, or when someone is about to report a CLEAN result from a sweep. This is not a checklist generator and not a devops runbook tool — it is a discipline for producing one paste-ready, auditable artifact that a careful stranger could run without you in the room.\n---\n\n# run-card — the credential-free door\n\n## Since 2026-09-25: the card is a file the machine runs\n\nA study of 47 of our own cards (`c4\u002Fh\u002FRESEARCH-2026-09-25-run-cards.md`) found five failure modes:\n- **Asserted, not observed.** 9 of 11 re-issues came from something the author asserted about the\n  machine and never observed there (a path, a tool's arguments, a config location).\n- **Unsafe to re-run.** A step did harm when run twice, and nothing told the driver which step\n  they were on.\n- **Scope.** The one card spanning three repos flopped.\n- **Paste.** Pasting mangled commands.\n- **Results lost.** Most results never came home.\n\nSo a card with more than one step is now a `.rc` file, run by `rc1rn` (C4's `bin\u002Frc1rn`, shipped\nhere as `scripts\u002Frc1rn`, which needs nothing else; when the two differ, read the diff and carry the fix\nacross on purpose, in whichever direction it runs -- 2026-10-04 carried C4's run-once guard here):\n\n    sh scripts\u002Frc1rn CARD.rc          # where am I: the facts, then [x] done \u002F [>] next \u002F [ ] later\n    sh scripts\u002Frc1rn CARD.rc next     # do the next step; run it again whenever unsure\n\nNo runner? Run the card's steps by hand, facts first.\n\nThe discipline below is still the whole point; the runner is where it lives now:\n- **Coverage first** becomes `facts()`. Every `fact` and `need` is probed on the driver's machine\n  at run time and printed before anything runs. A `need` that doesn't hold stops the run with what\n  was seen and what was needed. Never write a path or a tool's usage from memory: probe it, or\n  make it a `need`.\n- **Idempotence** is a `\u003Cstep>_done` test that runs before its step. A done step is skipped, so\n  re-running is always safe and `status` always knows the place. A step that runs clean but misses\n  its effect is reported as the card's fault, not the driver's.\n- **ABORT** is a failing step or an unmet need. Anything that can't be undone gets a\n  `\u003Cstep>_confirm` question and runs only on the word yes.\n- **One purpose per card.** A turn that touches three repos is three cards, or one card with one\n  step per repo, never one step doing all three.\n- **Disposition** is a step like any other (unset the token, remove the bag), with its own\n  done-test.\n- **The return trip** is `\u003Ccard>.log`, beside the card on the shared folder. The runner writes it;\n  the author reads it. The driver's \"tell me\" shrinks to \"done\", or to the one STOP line.\n- **Rehearse before handing over.** Run the card in the sandbox against a copy of the tree (a local\n  bare repo for pushes, a mock for any API) until `status` reads ALL DONE, then hand it over.\n\nA paste card (the rest of this page) is still right for a machine with no c4 on it. It keeps the\nread-order, the observable per step, and the ABORT line, and it is rehearsed like any other.\n\nA run-card is what lets someone who did not write the steps run them **correctly, on a real\nsystem, without you standing behind them.** It asks for time and care. It does not ask for\ngenius, seniority, or a credential. That is the whole point of it — a card is a door that\nanyone willing to be careful can walk through.\n\nIt exists because of a specific, repeated discovery: **the operator is rarely the weak\npart.** The weak part is a step whose result gets read in the wrong order, an absence\nreported as a clean bill of health, an instrument pointed at the wrong window, or a\nconclusion that travels without the bound it was born with. A card is not a reminder to be\ncareful. **A card is a measurement scheduled in advance** — it names the instrument, fixes\nthe order the answers are read in, and states what stops the run.\n\n## The one thing to internalize\n\n> **A card never says \"be careful.\" It says: run this; here is what the answer means; here is\n> what stops you.**\n\nIf you find yourself writing exhortation into a card, you have written a sermon. Delete it and\nwrite a step with an observable instead.\n\n## The furniture (paste this into the session FIRST)\n\nEvery card opens with a field block, **comment-prefixed so it pastes into the shell.** This is\nnot decoration. The transcript is the evidence — and a tape that shows *commands* but not\ntheir *authorization* cannot be tied back to the card that licensed them. With the furniture\nin the shell history, **the tape itself proves what the run was permitted to do**, and a cold\nreviewer never has to go looking for the card. Card and trail become one artifact.\n\n    # ============================================================================\n    # CARD ID    : RUNCARD-\u003Cdate>-\u003Cnn>-\u003Cslug>     (supersede, never edit)\n    # PURPOSE    : one sentence — the QUESTION this run answers\n    # GATE       : what authorizes this (whose ruling, when) — or \"none\", said plainly\n    # DRIVER     : the human at the keyboard\n    # SIGNER     : who signs which output, on whose machine (keys never travel)\n    # PRECOND    : what must already be true, checked aloud before step 1\n    # WRITES     : EVERY write this card makes, named. \"Read-only\" must MEAN it —\n    #              your own scratch dir is a write, and it gets declared, not assumed\n    # TRAIL      : the label comment each step opens with\n    # BAG        : one dated dir; everything tees into it; MANIFEST before the hop\n    # HOMECOMING : pile-then-one-hop, or quick-turns — DECIDED HERE, with the reason\n    # DISPOSITION: what gets DESTROYED, when, and who records it\n    # ABORT      : the conditions that stop the run (park it; do not argue with it)\n    # ============================================================================\n\n## The read-order, and it is the load-bearing rule\n\nWhen a step sweeps for something, the card **states the order the output is read in**:\n\n> ### COVERAGE → POSITIVE CONTROL → TARGETS. Always. In that order.\n\n**Coverage first.** What window does the instrument actually see? Retention, scope, host list,\ndate range. State it *before* the result, where it cannot be skipped.\n\n**Positive control second.** Did the sweep find something it *should* have found? A search that\nreturns nothing proves nothing unless the same search demonstrably finds a thing you know is\nthere. **Zero on the control means the instrument is blind — the sweep is VOID, not clean.**\n\n**Targets last.** Only now does a hit or a miss mean anything at all.\n\n**The worked example, and it is why this rule exists.** A sweep of a host's authentication logs\nfor two suspect SSH keys returned `(no hits)`, `(no hits)`, `(no hits)`. The positive control\nwas gorgeous — 74,103 accepted logins by real, named users. The instrument was perfect.\n\nRead targets-first, and you write *\"host clean — the bound widens to five hosts\"* into a\nsecurity finding going to a national foundation.\n\nRead coverage-first, and the **very first line** says the logs only reach back six weeks — and\nthe events under investigation are **five weeks before that**. The sweep is *clean and silent*.\nIt is a working instrument pointed at a window that does not contain the events. It proves\nnothing, and the honest card says so and **does not count that host toward the negative.**\n\nThe coverage line was the only thing standing between a careful team and a false claim in a\npublished report. **That is what the ordering is for.**\n\n## What a card must REFUSE to claim\n\nThis is the part that makes a card trustworthy rather than merely tidy:\n\n- **An absence is not a clean result.** \"We didn't find it\" is only a finding if you *looked*,\n  and it is only *worth* something if you say where you looked. **Bound every negative** — in\n  the artifact, not in your head.\n- **An unreachable host is a gap, not a clean host.** Write the gap into the output.\n- **A hash is the start of reading, not a substitute for it.** Verifying a checksum proves the\n  bytes didn't change. It says nothing about what they *say*. (A patch report can pass its\n  checksum perfectly and still say the rollout failed and two internet-facing hosts are\n  unpatched. Read the file.)\n- **A note about a check is not the check.** \"We swept, it was clean\" written in a summary is a\n  *claim about* evidence. It is not evidence. If you cannot name the run that produced a fact,\n  the fact is data.\n- **A bare numeric ID is never a safe search term.** It will match ports, PIDs, and the\n  fractional-seconds field of a timestamp, and hand you a phantom incident. Anchor on the name.\n- **Prefer the interface that decides over the file you think it reads.** Ask `sshd -T`, not a\n  regex over the config that will miss a tab.\n\n## Steps\n\nNumbered. Paste-ready. **Absolute paths** — `~` is not a path, it is an assumption about who\nyou are, and it will resolve differently for root. Syntax-check every multi-line block before\nyou hand it to a driver; a card must be *pasteable*, not *interpretable*.\n\nEach step names **the observable that proves it ran** — and each step opens with a label\ncomment, so the shell history reads back as a narrative. Shell history is evidence. Write it on\npurpose.\n\n**Gate steps.** Where a later step's meaning *depends* on an earlier answer, say so, and make\nthe gate **readable at the keyboard** — put the expected value right there on the card so the\ndriver can decide without phoning anyone. A gate that requires a round-trip is not a gate; it's\na bottleneck.\n\n## Disposition — the field people forget, and the one that protects strangers\n\nEvery run leaves residue: extracted archives, working copies, staging directories, a bag on a\nhost that isn't yours. And the residue is very often **not about your question and not yours to\nkeep** — a single system's auth log carries the login records of *every person who ever used\nit*.\n\nSo the card says, in advance:\n\n1. **What is transacted** — the raw material, most of which is other people's.\n2. **What must not travel** — *the analysis runs where the data lands; only the ANSWER comes\n   home.* Bring the counts, the hit\u002Fno-hit, the hashes. Not the log.\n3. **What is destroyed, when, and who writes it down** — with a trigger (\"after the outputs are\n   verified, and not before\") and a receipt.\n\nPreserve-before-act governs the **evidence**. It does not license leaving a fleet's user data on\npersonal infrastructure. **A run with no disposition step is not finished. It is abandoned.**\n\n## Tone at the keyboard\n\nA card is often being run by someone newer than you, on a system that scares them a little. The\nregister matters — a door that makes people feel stupid is not a door.\n\nWarmth on a passing gate: *\"nice — that's the disk continuity proved, keep going.\"* A cadence\ninstruction when the output needs thinking about rather than scrolling past: *\"Okay, stop for a\nmoment. Let's read what we're actually seeing.\"*\n\n**But the mood colors the encouragement, never the verdict.** Warmth attached to a *failing*\ncheck is poison. A STOP is a STOP, and it is never softened to spare anyone's feelings —\nincluding your own.\n\n## When the run comes back\n\nRead it. **All of it.** A hash that verifies is not a file that has been read, and a faithful\ntranscript of an artifact is not the artifact — those are *two sources*, and agreement between\nthem is what makes a thing evidence rather than data.\n\nThen say what it closed, what it **didn't**, and what is still open — **titled, with an owner.**\nAn unfinished thread handed on *with* a road-map is discharged. Handed on *without* one, it is\ndropped, and it is wearing a park's clothing.\n\n## The rule that governs all of it\n\n**No card, no run.** Not because ceremony is good, but because the card is the thing that lets\nthe next person — a volunteer, a stranger, you in three weeks with none of this in your head —\ndo the work correctly and prove that they did.\n\n## How this skill can fail (falsifiers)\n\n- **The runner drifted from its source.** fails if `scripts\u002Frc1rn` differs from C4's `bin\u002Frc1rn`; check: `cmp scripts\u002Frc1rn \"$C4_ROOT\u002Fbin\u002Frc1rn\"`, then C4's `sh tests\u002Frc1rn-tests.sh` and `--prove-red` (12\u002F12 and PASS on 2026-09-27).\n- **A void sweep counted clean.** fails if a card reports a negative when its control found zero or its coverage window misses the event dates; check: the step's output reads COVERAGE, then CONTROL above 0, then TARGETS.\n- **An undeclared write.** fails if the run wrote anywhere not named under WRITES; check: compare the bag's MANIFEST and `find \u003Cdirs> -newer \u003Ccard>.log` against the WRITES field.\n\n\u003C!-- footer: minted by bin\u002Fft1mt from conventions\u002Fhouse.env and conventions\u002FFOOTERS.org; edit those, not this -->\n*Version 1.1.0: edition revised from 1.0.1 on 2026-10-10; spine: 2026-09-23.*\n\nCopyright 2026 Corwin Brust \u003Ccorwin@bru.st> and Contributors; CC-BY-SA4: https:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby-sa\u002F4.0\u002F (scripts GPL-3.0-or-later); Mentat (for Corwin; claude-opus-5-5)\n\u003C!-- \u002Ffooter -->\n","# run-card — the credential-free door\n\n## Since 2026-09-25: the card is a file the machine runs\n\nA study of 47 of our own cards (`c4\u002Fh\u002FRESEARCH-2026-09-25-run-cards.md`) found five failure modes:\n- **Asserted, not observed.** 9 of 11 re-issues came from something the author asserted about the\n  machine and never observed there (a path, a tool's arguments, a config location).\n- **Unsafe to re-run.** A step did harm when run twice, and nothing told the driver which step\n  they were on.\n- **Scope.** The one card spanning three repos flopped.\n- **Paste.** Pasting mangled commands.\n- **Results lost.** Most results never came home.\n\nSo a card with more than one step is now a `.rc` file, run by `rc1rn` (C4's `bin\u002Frc1rn`, shipped\nhere as `scripts\u002Frc1rn`, which needs nothing else; when the two differ, read the diff and carry the fix\nacross on purpose, in whichever direction it runs -- 2026-10-04 carried C4's run-once guard here):\n\n    sh scripts\u002Frc1rn CARD.rc          # where am I: the facts, then [x] done \u002F [>] next \u002F [ ] later\n    sh scripts\u002Frc1rn CARD.rc next     # do the next step; run it again whenever unsure\n\nNo runner? Run the card's steps by hand, facts first.\n\nThe discipline below is still the whole point; the runner is where it lives now:\n- **Coverage first** becomes `facts()`. Every `fact` and `need` is probed on the driver's machine\n  at run time and printed before anything runs. A `need` that doesn't hold stops the run with what\n  was seen and what was needed. Never write a path or a tool's usage from memory: probe it, or\n  make it a `need`.\n- **Idempotence** is a `\u003Cstep>_done` test that runs before its step. A done step is skipped, so\n  re-running is always safe and `status` always knows the place. A step that runs clean but misses\n  its effect is reported as the card's fault, not the driver's.\n- **ABORT** is a failing step or an unmet need. Anything that can't be undone gets a\n  `\u003Cstep>_confirm` question and runs only on the word yes.\n- **One purpose per card.** A turn that touches three repos is three cards, or one card with one\n  step per repo, never one step doing all three.\n- **Disposition** is a step like any other (unset the token, remove the bag), with its own\n  done-test.\n- **The return trip** is `\u003Ccard>.log`, beside the card on the shared folder. The runner writes it;\n  the author reads it. The driver's \"tell me\" shrinks to \"done\", or to the one STOP line.\n- **Rehearse before handing over.** Run the card in the sandbox against a copy of the tree (a local\n  bare repo for pushes, a mock for any API) until `status` reads ALL DONE, then hand it over.\n\nA paste card (the rest of this page) is still right for a machine with no c4 on it. It keeps the\nread-order, the observable per step, and the ABORT line, and it is rehearsed like any other.\n\nA run-card is what lets someone who did not write the steps run them **correctly, on a real\nsystem, without you standing behind them.** It asks for time and care. It does not ask for\ngenius, seniority, or a credential. That is the whole point of it — a card is a door that\nanyone willing to be careful can walk through.\n\nIt exists because of a specific, repeated discovery: **the operator is rarely the weak\npart.** The weak part is a step whose result gets read in the wrong order, an absence\nreported as a clean bill of health, an instrument pointed at the wrong window, or a\nconclusion that travels without the bound it was born with. A card is not a reminder to be\ncareful. **A card is a measurement scheduled in advance** — it names the instrument, fixes\nthe order the answers are read in, and states what stops the run.\n\n## The one thing to internalize\n\n> **A card never says \"be careful.\" It says: run this; here is what the answer means; here is\n> what stops you.**\n\nIf you find yourself writing exhortation into a card, you have written a sermon. Delete it and\nwrite a step with an observable instead.\n\n## The furniture (paste this into the session FIRST)\n\nEvery card opens with a field block, **comment-prefixed so it pastes into the shell.** This is\nnot decoration. The transcript is the evidence — and a tape that shows *commands* but not\ntheir *authorization* cannot be tied back to the card that licensed them. With the furniture\nin the shell history, **the tape itself proves what the run was permitted to do**, and a cold\nreviewer never has to go looking for the card. Card and trail become one artifact.\n\n    # ============================================================================\n    # CARD ID    : RUNCARD-\u003Cdate>-\u003Cnn>-\u003Cslug>     (supersede, never edit)\n    # PURPOSE    : one sentence — the QUESTION this run answers\n    # GATE       : what authorizes this (whose ruling, when) — or \"none\", said plainly\n    # DRIVER     : the human at the keyboard\n    # SIGNER     : who signs which output, on whose machine (keys never travel)\n    # PRECOND    : what must already be true, checked aloud before step 1\n    # WRITES     : EVERY write this card makes, named. \"Read-only\" must MEAN it —\n    #              your own scratch dir is a write, and it gets declared, not assumed\n    # TRAIL      : the label comment each step opens with\n    # BAG        : one dated dir; everything tees into it; MANIFEST before the hop\n    # HOMECOMING : pile-then-one-hop, or quick-turns — DECIDED HERE, with the reason\n    # DISPOSITION: what gets DESTROYED, when, and who records it\n    # ABORT      : the conditions that stop the run (park it; do not argue with it)\n    # ============================================================================\n\n## The read-order, and it is the load-bearing rule\n\nWhen a step sweeps for something, the card **states the order the output is read in**:\n\n> ### COVERAGE → POSITIVE CONTROL → TARGETS. Always. In that order.\n\n**Coverage first.** What window does the instrument actually see? Retention, scope, host list,\ndate range. State it *before* the result, where it cannot be skipped.\n\n**Positive control second.** Did the sweep find something it *should* have found? A search that\nreturns nothing proves nothing unless the same search demonstrably finds a thing you know is\nthere. **Zero on the control means the instrument is blind — the sweep is VOID, not clean.**\n\n**Targets last.** Only now does a hit or a miss mean anything at all.\n\n**The worked example, and it is why this rule exists.** A sweep of a host's authentication logs\nfor two suspect SSH keys returned `(no hits)`, `(no hits)`, `(no hits)`. The positive control\nwas gorgeous — 74,103 accepted logins by real, named users. The instrument was perfect.\n\nRead targets-first, and you write *\"host clean — the bound widens to five hosts\"* into a\nsecurity finding going to a national foundation.\n\nRead coverage-first, and the **very first line** says the logs only reach back six weeks — and\nthe events under investigation are **five weeks before that**. The sweep is *clean and silent*.\nIt is a working instrument pointed at a window that does not contain the events. It proves\nnothing, and the honest card says so and **does not count that host toward the negative.**\n\nThe coverage line was the only thing standing between a careful team and a false claim in a\npublished report. **That is what the ordering is for.**\n\n## What a card must REFUSE to claim\n\nThis is the part that makes a card trustworthy rather than merely tidy:\n\n- **An absence is not a clean result.** \"We didn't find it\" is only a finding if you *looked*,\n  and it is only *worth* something if you say where you looked. **Bound every negative** — in\n  the artifact, not in your head.\n- **An unreachable host is a gap, not a clean host.** Write the gap into the output.\n- **A hash is the start of reading, not a substitute for it.** Verifying a checksum proves the\n  bytes didn't change. It says nothing about what they *say*. (A patch report can pass its\n  checksum perfectly and still say the rollout failed and two internet-facing hosts are\n  unpatched. Read the file.)\n- **A note about a check is not the check.** \"We swept, it was clean\" written in a summary is a\n  *claim about* evidence. It is not evidence. If you cannot name the run that produced a fact,\n  the fact is data.\n- **A bare numeric ID is never a safe search term.** It will match ports, PIDs, and the\n  fractional-seconds field of a timestamp, and hand you a phantom incident. Anchor on the name.\n- **Prefer the interface that decides over the file you think it reads.** Ask `sshd -T`, not a\n  regex over the config that will miss a tab.\n\n## Steps\n\nNumbered. Paste-ready. **Absolute paths** — `~` is not a path, it is an assumption about who\nyou are, and it will resolve differently for root. Syntax-check every multi-line block before\nyou hand it to a driver; a card must be *pasteable*, not *interpretable*.\n\nEach step names **the observable that proves it ran** — and each step opens with a label\ncomment, so the shell history reads back as a narrative. Shell history is evidence. Write it on\npurpose.\n\n**Gate steps.** Where a later step's meaning *depends* on an earlier answer, say so, and make\nthe gate **readable at the keyboard** — put the expected value right there on the card so the\ndriver can decide without phoning anyone. A gate that requires a round-trip is not a gate; it's\na bottleneck.\n\n## Disposition — the field people forget, and the one that protects strangers\n\nEvery run leaves residue: extracted archives, working copies, staging directories, a bag on a\nhost that isn't yours. And the residue is very often **not about your question and not yours to\nkeep** — a single system's auth log carries the login records of *every person who ever used\nit*.\n\nSo the card says, in advance:\n\n1. **What is transacted** — the raw material, most of which is other people's.\n2. **What must not travel** — *the analysis runs where the data lands; only the ANSWER comes\n   home.* Bring the counts, the hit\u002Fno-hit, the hashes. Not the log.\n3. **What is destroyed, when, and who writes it down** — with a trigger (\"after the outputs are\n   verified, and not before\") and a receipt.\n\nPreserve-before-act governs the **evidence**. It does not license leaving a fleet's user data on\npersonal infrastructure. **A run with no disposition step is not finished. It is abandoned.**\n\n## Tone at the keyboard\n\nA card is often being run by someone newer than you, on a system that scares them a little. The\nregister matters — a door that makes people feel stupid is not a door.\n\nWarmth on a passing gate: *\"nice — that's the disk continuity proved, keep going.\"* A cadence\ninstruction when the output needs thinking about rather than scrolling past: *\"Okay, stop for a\nmoment. Let's read what we're actually seeing.\"*\n\n**But the mood colors the encouragement, never the verdict.** Warmth attached to a *failing*\ncheck is poison. A STOP is a STOP, and it is never softened to spare anyone's feelings —\nincluding your own.\n\n## When the run comes back\n\nRead it. **All of it.** A hash that verifies is not a file that has been read, and a faithful\ntranscript of an artifact is not the artifact — those are *two sources*, and agreement between\nthem is what makes a thing evidence rather than data.\n\nThen say what it closed, what it **didn't**, and what is still open — **titled, with an owner.**\nAn unfinished thread handed on *with* a road-map is discharged. Handed on *without* one, it is\ndropped, and it is wearing a park's clothing.\n\n## The rule that governs all of it\n\n**No card, no run.** Not because ceremony is good, but because the card is the thing that lets\nthe next person — a volunteer, a stranger, you in three weeks with none of this in your head —\ndo the work correctly and prove that they did.\n\n## How this skill can fail (falsifiers)\n\n- **The runner drifted from its source.** fails if `scripts\u002Frc1rn` differs from C4's `bin\u002Frc1rn`; check: `cmp scripts\u002Frc1rn \"$C4_ROOT\u002Fbin\u002Frc1rn\"`, then C4's `sh tests\u002Frc1rn-tests.sh` and `--prove-red` (12\u002F12 and PASS on 2026-09-27).\n- **A void sweep counted clean.** fails if a card reports a negative when its control found zero or its coverage window misses the event dates; check: the step's output reads COVERAGE, then CONTROL above 0, then TARGETS.\n- **An undeclared write.** fails if the run wrote anywhere not named under WRITES; check: compare the bag's MANIFEST and `find \u003Cdirs> -newer \u003Ccard>.log` against the WRITES field.\n\n\u003C!-- footer: minted by bin\u002Fft1mt from conventions\u002Fhouse.env and conventions\u002FFOOTERS.org; edit those, not this -->\n*Version 1.1.0: edition revised from 1.0.1 on 2026-10-10; spine: 2026-09-23.*\n\nCopyright 2026 Corwin Brust \u003Ccorwin@bru.st> and Contributors; CC-BY-SA4: https:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby-sa\u002F4.0\u002F (scripts GPL-3.0-or-later); Mentat (for Corwin; claude-opus-5-5)\n\u003C!-- \u002Ffooter -->\n",{"name":5,"description":7},"main","0b0a0f665f67605c3bc1d43500eea26ef3079a97","skills\u002Frun-card","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden","https:\u002F\u002Fgithub.com\u002Finputloop","2026-10-14 18:29:39",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add inputloop\u002Fgarden --skill run-card",{"tool":36,"command":37},"bunx","bunx skills add inputloop\u002Fgarden --skill run-card",{"tool":39,"command":40},"pnpm","pnpm dlx skills add inputloop\u002Fgarden --skill run-card","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002FSKILL.md",true,[44,50,53,56,59,65,69,73,76,79,83,86,90,94,97,100,106],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},".arc\u002F2026-09\u002Fsignature-2026-09-23_pre-header-pass.asc","OTHER","其他",659,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-09\u002Fsignature-2026-09-23_pre-header-pass.asc",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":52},".arc\u002F2026-09\u002Fsignature-2026-09-24_162128Z_pre-manifest.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-09\u002Fsignature-2026-09-24_162128Z_pre-manifest.asc",{"path":54,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":55},".arc\u002F2026-09\u002Fsignature-2026-09-25_202226Z_pre-manifest.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-09\u002Fsignature-2026-09-25_202226Z_pre-manifest.asc",{"path":57,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":58},".arc\u002F2026-09\u002Fsignature-2026-09-27_203835Z_pre-manifest.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-09\u002Fsignature-2026-09-27_203835Z_pre-manifest.asc",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},".arc\u002F2026-09\u002FSKILL-2026-09-27_pre-hardening.md","REFERENCE","参考文档",12927,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-09\u002FSKILL-2026-09-27_pre-hardening.md",{"path":66,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":67,"sourceHtmlUrl":68},".arc\u002F2026-09\u002Fskill-manifest-2026-09-23_pre-header-pass",77,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-09\u002Fskill-manifest-2026-09-23_pre-header-pass",{"path":70,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":71,"sourceHtmlUrl":72},".arc\u002F2026-09\u002Fskill-manifest-2026-09-24_162128Z_pre-manifest",322,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-09\u002Fskill-manifest-2026-09-24_162128Z_pre-manifest",{"path":74,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":67,"sourceHtmlUrl":75},".arc\u002F2026-09\u002Fskill-manifest-2026-09-25_202226Z_pre-manifest","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-09\u002Fskill-manifest-2026-09-25_202226Z_pre-manifest",{"path":77,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":67,"sourceHtmlUrl":78},".arc\u002F2026-09\u002Fskill-manifest-2026-09-27_203835Z_pre-manifest","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-09\u002Fskill-manifest-2026-09-27_203835Z_pre-manifest",{"path":80,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":81,"sourceHtmlUrl":82},".arc\u002F2026-10\u002Frc1rn-2026-09-25_pre-loop-guard",6820,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-10\u002Frc1rn-2026-09-25_pre-loop-guard",{"path":84,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":85},".arc\u002F2026-10\u002Fsignature-2026-10-10_104827Z_pre-manifest.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-10\u002Fsignature-2026-10-10_104827Z_pre-manifest.asc",{"path":87,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":88,"sourceHtmlUrl":89},".arc\u002F2026-10\u002FSKILL-2026-10-04_pre-c4-optional.md",13709,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-10\u002FSKILL-2026-10-04_pre-c4-optional.md",{"path":91,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":92,"sourceHtmlUrl":93},".arc\u002F2026-10\u002Fskill-manifest-2026-10-10_104827Z_pre-manifest",236,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.arc\u002F2026-10\u002Fskill-manifest-2026-10-10_104827Z_pre-manifest",{"path":95,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":96},".signature.asc","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.signature.asc",{"path":98,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":92,"sourceHtmlUrl":99},".skill-manifest","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002F.skill-manifest",{"path":101,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Frc1rn","SCRIPT","脚本",7252,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002Fscripts\u002Frc1rn",{"path":107,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":108,"sourceHtmlUrl":109},"tests.sh",11689,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Frun-card\u002Ftests.sh",[111,117,123,130,137,144],{"skillNo":112,"name":113,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M7EPTX6X52ZPGVQZHKVJ7FAZ","alpha","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-d\u002Fbr1in\u002Fours\u002Fskills\u002Falpha\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":19},"01M7EPTWCTS80QHFQ2ND3A1CW1","gamma","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-d\u002Fbr1in\u002Fours\u002FSOFT-SKILLS\u002Fgamma\u002FSKILL.md",[],[],{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":19},"01M7EPTV3K3SCTRP0DR6BMMKR0","quiet","A fixture skill that declares no preferences, so skill.quiet.* has no reader.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-a\u002Fdeclared\u002Fsoft\u002Fquiet\u002FSKILL.md",[],[],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":19},"01M7EPTSG0VE67F6PFAC0XJDQ4","demo","A fixture skill for tests\u002Fprefs-declared-spec.rb; it declares two preferences inline.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-a\u002Fdeclared\u002Fsoft\u002Fdemo\u002FSKILL.md",[],[],{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":19},"01M7EPTP0PM5WPTFBHPXBCFM5C","concise","Synthesized by polygram from memory tag 'concise'. explicitly flagged. Review and tighten this description before relying on it for triggering.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fconcise\u002FSKILL.md",[],[],{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":19},"01M7EPTAETQ62DJA8ZFEEBBZF0","writing-forms","Which writing form a dated deliverable takes in the shop, and the five techniques every form shares. Use whenever someone is about to write a dated deliverable — \"which form is this?\", \"write it up\", \"land a note \u002F card \u002F model \u002F lens\", \"what shape does a … take\", \"is there a form for this\", or when a new PREFIX-date-slug filename is about to be minted. Carries the rule that a deliverable picks ONE form and says so in its filename, points at the register c\u002Fwf (columns d\u002Fc\u002Fwf) as the source of truth, names the most-used forms, the five cross-cutting techniques (two piles · cite at the act · a falsifier on every concern · the pair rule · his words), how a new form is born, and the fence on notes other sessions wrote. Not rolls (report kinds and their guards), not reformat-prompt (the REFORMAT pair), not run-card (the RUNCARD), not skill-creator (skills). Owns the FORM, not the content.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-forms\u002FSKILL.md",[],[]]