[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M799VHDEWZ2KJG2C3G46YYRW":3,"skill-same:01M799VHDEWZ2KJG2C3G46YYRW":67},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M799VHDEWZ2KJG2C3G46YYRW","audit-receipt",null,"Audit a sealed runx receipt for governance, comparing the authority a run exercised against what it was granted, and flag over-reach, ungated mutation, unrecorded refusals, or exposed secret material.","ZachDreamZ\u002Frunx","ZachDreamZ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F22769595?v=4","01M799NTP9N5VYWB4JY50MC7Y3","NexusCore","01M799NTQ1AYT8TZC0XTSEZXDJ",0,"MIT","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Faudit-receipt\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: audit-receipt\ndescription: Audit a sealed runx receipt for governance, comparing the authority a run exercised against what it was granted, and flag over-reach, ungated mutation, unrecorded refusals, or exposed secret material.\nrunx:\n  category: security\n---\n\n# Receipt Auditor\n\nAudit a sealed run for authority over-reach, binding the review to its native\nreceipt identity and verification posture.\n\nRunx seals a receipt for every run. This skill resolves the exact receipt id\nthrough `ledger read`, then uses a bounded authority and act summary for details\nthat native history deliberately does not hydrate. It answers one governance\nquestion: did the run stay inside the authority it was granted? It flags scopes\nexercised that were never granted, mutating acts that ran without an approval\ngate, refusals that were not recorded, and any raw secret material that leaked\ninto the receipt. It pairs with `least-privilege`: that one narrows a\ngrant from usage, this one verifies a run honored its grant.\n\n## What this skill does\n\n1. **Read the proof and the acts.** From the receipt, extract the granted\n   authority (the proof) and the scopes the acts actually exercised.\n2. **Diff exercised against granted.** Any exercised scope not covered by the\n   proof is over-reach.\n3. **Check the gates.** Every mutating act must show an approval gate in the\n   receipt; an ungated mutation is an anomaly.\n4. **Check exposure.** The receipt must carry only hashed material references; a\n   raw secret in the receipt is a leak.\n5. **Verdict.** `clean`, `anomaly`, or `needs_more_evidence`, with the exact\n   findings and a recommendation for each anomaly.\n\n## Core principles\n\n- **The receipt is the evidence.** Audit what the receipt records, not what the\n  skill claims it did.\n- **Granted is the ceiling.** Exercised authority must be a subset of the proof;\n  anything beyond is over-reach, full stop.\n- **Mutation needs a gate.** A mutating act with no approval gate in the receipt\n  is an anomaly even if it succeeded.\n- **No raw material.** A receipt must reference material by hash; raw credential\n  material in a receipt is a leak, not a convenience.\n- **Absence of evidence is not clean.** With no receipt or an unattributable\n  one, return `needs_more_evidence`, never `clean`.\n\n## When to use this skill\n\n- Post-run governance audit of a sealed, successful run.\n- Spot-checking that a skill honored its authority bound in production.\n- Before promoting a skill toward a higher trust posture.\n\n## When not to use this skill\n\n- To diagnose a failed run and propose a fix. That is `review-receipt`\n  (failure-to-improvement). This skill audits a sealed run for over-reach\n  (success-to-governance); the two are different lenses on a receipt.\n- To narrow a grant from observed usage. That is `least-privilege`.\n\n## Diagnostics\n\n- `receipt.authority.over_reach` (error): an exercised scope is not covered by\n  the authority proof.\n- `receipt.mutation.ungated` (error): a mutating act ran without an approval gate\n  recorded in the receipt.\n- `receipt.refusal.unrecorded` (warning): a denied request is not reflected as a\n  sealed refusal.\n- `receipt.material.exposed` (error): raw credential material appears in the\n  receipt instead of a hash reference.\n- `receipt.clean` (info): exercised authority is within the grant, mutations are\n  gated, and no material is exposed.\n\n## Procedure\n\n1. Resolve `receipt_id` through the native ledger and verify the matched tree\n   when keys are available. Use the provided sanitized `receipt_summary` for\n   detailed authority and act evidence.\n2. Extract the authority proof, granted scopes, acts, approvals, refusals,\n   material references, and receipt signature metadata.\n3. Normalize exercised scopes from the acts and compare them with the granted\n   scopes. Exercised must be a subset of granted.\n4. Identify mutating acts and confirm each has an approval gate recorded in the\n   receipt.\n5. Check that denied requests appear as sealed refusals when the receipt records\n   the attempt.\n6. Scan receipt-visible material for raw credentials or secret-bearing payloads.\n7. Return a verdict with findings, recommendations, and the success checkpoint.\n\n## Edge cases and stop conditions\n\n- **Missing receipt:** return `needs_more_evidence`; never infer a clean run.\n- **Unattributable receipt:** return `needs_more_evidence` when the receipt\n  cannot be tied to the run under audit.\n- **Malformed proof:** return `needs_more_evidence` unless enough normalized\n  grant data is supplied separately.\n- **Unknown scope name:** treat it as over-reach unless the grant explicitly\n  covers it.\n- **Mutation without recorded gate:** emit `receipt.mutation.ungated` even if the\n  mutation succeeded and the outcome looks correct.\n- **Raw token, key, or credential in the receipt:** emit\n  `receipt.material.exposed` and recommend revocation\u002Frotation.\n\n## Output schema (`receipt_audit`)\n\n```yaml\ndecision: ready | needs_more_evidence\nrun_ref: string\ngranted_scopes: [string]\nexercised_scopes: [string]\nrefusals: [string]\nfindings:\n  - id: string\n    severity: error | warning | info\n    message: string\nverdict: clean | anomaly | needs_more_evidence\nrationale: string\nrecommendations: [string]\nsuccess_checkpoint:\n  milestone: string\n  description: string\n```\n\nA `clean` verdict requires zero `error` findings.\n\n## Worked example\n\nA sealed run was granted `repo.read`. The receipt shows the acts exercised only\n`repo.read`, every act is an observation (no mutation), and material is\nreferenced by hash. Exercised is a subset of granted, no mutation to gate, no\nexposure: `verdict: clean`. Had an act exercised `repo.write` while the proof\ngranted only `repo.read`, that would raise `receipt.authority.over_reach` and a\n`verdict: anomaly` with a recommendation to revoke the run's grant and\ninvestigate.\n\n## Inputs\n\n- `receipt_id` (optional): the receipt id to audit.\n- `receipt_summary` (optional): a sanitized receipt or its acts\u002Fproof summary\n  when the full receipt is not available.\n- `granted_scopes` (optional): the authority the run was granted, when not\n  derivable from the receipt alone.\n- `objective` (optional): operator intent that focuses the audit.\n- `receipt_rows` (optional): native-projection rows for deterministic replay;\n  live runs resolve `receipt_id` from the configured receipt store.\n\nAt least one of `receipt_id` or `receipt_summary` is required; with neither, the\nskill returns `needs_more_evidence`.\n","# Receipt Auditor\n\nAudit a sealed run for authority over-reach, binding the review to its native\nreceipt identity and verification posture.\n\nRunx seals a receipt for every run. This skill resolves the exact receipt id\nthrough `ledger read`, then uses a bounded authority and act summary for details\nthat native history deliberately does not hydrate. It answers one governance\nquestion: did the run stay inside the authority it was granted? It flags scopes\nexercised that were never granted, mutating acts that ran without an approval\ngate, refusals that were not recorded, and any raw secret material that leaked\ninto the receipt. It pairs with `least-privilege`: that one narrows a\ngrant from usage, this one verifies a run honored its grant.\n\n## What this skill does\n\n1. **Read the proof and the acts.** From the receipt, extract the granted\n   authority (the proof) and the scopes the acts actually exercised.\n2. **Diff exercised against granted.** Any exercised scope not covered by the\n   proof is over-reach.\n3. **Check the gates.** Every mutating act must show an approval gate in the\n   receipt; an ungated mutation is an anomaly.\n4. **Check exposure.** The receipt must carry only hashed material references; a\n   raw secret in the receipt is a leak.\n5. **Verdict.** `clean`, `anomaly`, or `needs_more_evidence`, with the exact\n   findings and a recommendation for each anomaly.\n\n## Core principles\n\n- **The receipt is the evidence.** Audit what the receipt records, not what the\n  skill claims it did.\n- **Granted is the ceiling.** Exercised authority must be a subset of the proof;\n  anything beyond is over-reach, full stop.\n- **Mutation needs a gate.** A mutating act with no approval gate in the receipt\n  is an anomaly even if it succeeded.\n- **No raw material.** A receipt must reference material by hash; raw credential\n  material in a receipt is a leak, not a convenience.\n- **Absence of evidence is not clean.** With no receipt or an unattributable\n  one, return `needs_more_evidence`, never `clean`.\n\n## When to use this skill\n\n- Post-run governance audit of a sealed, successful run.\n- Spot-checking that a skill honored its authority bound in production.\n- Before promoting a skill toward a higher trust posture.\n\n## When not to use this skill\n\n- To diagnose a failed run and propose a fix. That is `review-receipt`\n  (failure-to-improvement). This skill audits a sealed run for over-reach\n  (success-to-governance); the two are different lenses on a receipt.\n- To narrow a grant from observed usage. That is `least-privilege`.\n\n## Diagnostics\n\n- `receipt.authority.over_reach` (error): an exercised scope is not covered by\n  the authority proof.\n- `receipt.mutation.ungated` (error): a mutating act ran without an approval gate\n  recorded in the receipt.\n- `receipt.refusal.unrecorded` (warning): a denied request is not reflected as a\n  sealed refusal.\n- `receipt.material.exposed` (error): raw credential material appears in the\n  receipt instead of a hash reference.\n- `receipt.clean` (info): exercised authority is within the grant, mutations are\n  gated, and no material is exposed.\n\n## Procedure\n\n1. Resolve `receipt_id` through the native ledger and verify the matched tree\n   when keys are available. Use the provided sanitized `receipt_summary` for\n   detailed authority and act evidence.\n2. Extract the authority proof, granted scopes, acts, approvals, refusals,\n   material references, and receipt signature metadata.\n3. Normalize exercised scopes from the acts and compare them with the granted\n   scopes. Exercised must be a subset of granted.\n4. Identify mutating acts and confirm each has an approval gate recorded in the\n   receipt.\n5. Check that denied requests appear as sealed refusals when the receipt records\n   the attempt.\n6. Scan receipt-visible material for raw credentials or secret-bearing payloads.\n7. Return a verdict with findings, recommendations, and the success checkpoint.\n\n## Edge cases and stop conditions\n\n- **Missing receipt:** return `needs_more_evidence`; never infer a clean run.\n- **Unattributable receipt:** return `needs_more_evidence` when the receipt\n  cannot be tied to the run under audit.\n- **Malformed proof:** return `needs_more_evidence` unless enough normalized\n  grant data is supplied separately.\n- **Unknown scope name:** treat it as over-reach unless the grant explicitly\n  covers it.\n- **Mutation without recorded gate:** emit `receipt.mutation.ungated` even if the\n  mutation succeeded and the outcome looks correct.\n- **Raw token, key, or credential in the receipt:** emit\n  `receipt.material.exposed` and recommend revocation\u002Frotation.\n\n## Output schema (`receipt_audit`)\n\n```yaml\ndecision: ready | needs_more_evidence\nrun_ref: string\ngranted_scopes: [string]\nexercised_scopes: [string]\nrefusals: [string]\nfindings:\n  - id: string\n    severity: error | warning | info\n    message: string\nverdict: clean | anomaly | needs_more_evidence\nrationale: string\nrecommendations: [string]\nsuccess_checkpoint:\n  milestone: string\n  description: string\n```\n\nA `clean` verdict requires zero `error` findings.\n\n## Worked example\n\nA sealed run was granted `repo.read`. The receipt shows the acts exercised only\n`repo.read`, every act is an observation (no mutation), and material is\nreferenced by hash. Exercised is a subset of granted, no mutation to gate, no\nexposure: `verdict: clean`. Had an act exercised `repo.write` while the proof\ngranted only `repo.read`, that would raise `receipt.authority.over_reach` and a\n`verdict: anomaly` with a recommendation to revoke the run's grant and\ninvestigate.\n\n## Inputs\n\n- `receipt_id` (optional): the receipt id to audit.\n- `receipt_summary` (optional): a sanitized receipt or its acts\u002Fproof summary\n  when the full receipt is not available.\n- `granted_scopes` (optional): the authority the run was granted, when not\n  derivable from the receipt alone.\n- `objective` (optional): operator intent that focuses the audit.\n- `receipt_rows` (optional): native-projection rows for deterministic replay;\n  live runs resolve `receipt_id` from the configured receipt store.\n\nAt least one of `receipt_id` or `receipt_summary` is required; with neither, the\nskill returns `needs_more_evidence`.\n",{"name":5,"runx":24,"description":7},{"category":25},"security","main","fe90232960df6d9653e72e8d024a9d859e1ae524","skills\u002Faudit-receipt","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx","https:\u002F\u002Frunx.ai","https:\u002F\u002Fgithub.com\u002FZachDreamZ","https:\u002F\u002Fagentapigw.dpdns.org","Building Agent API Gateway — structured web data for AI agents. Consistent until I make it.","2026-07-17 04:21:10",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add ZachDreamZ\u002Frunx --skill audit-receipt",{"tool":41,"command":42},"bunx","bunx skills add ZachDreamZ\u002Frunx --skill audit-receipt",{"tool":44,"command":45},"pnpm","pnpm dlx skills add ZachDreamZ\u002Frunx --skill audit-receipt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Faudit-receipt\u002FSKILL.md",true,[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"fixtures\u002Fclean-run-within-grant.yaml","REFERENCE","参考文档",1738,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Faudit-receipt\u002Ffixtures\u002Fclean-run-within-grant.yaml",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"fixtures\u002Fmissing-receipt-needs-evidence.yaml",1087,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Faudit-receipt\u002Ffixtures\u002Fmissing-receipt-needs-evidence.yaml",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"fixtures\u002Fover-reach-flagged.yaml",2091,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Faudit-receipt\u002Ffixtures\u002Fover-reach-flagged.yaml",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"X.yaml",2460,"https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Faudit-receipt\u002FX.yaml",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M79A3PCWPN0YG6XG3X2YWGY4","zapier-handoff","Validate a runx execution context and hand off a governed payload to a Zapier Catch Hook with scoped auth, idempotency, and receipt expectations.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fzapier-handoff\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M79A3JPAJVDGX5AGXKHB6M58","x402-pay","Execute a governed x402 payment by delegating to the canonical spend flow with the x402 runtime path selected.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fx402-pay\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M79A3H7HHAQ5B4QCA0S2PPA3","work-plan","Decompose a build objective into governed runx execution steps.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fwork-plan\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M79A3ESQDZ6AQ3QASKYGYTNB","web-fetch","Fetch and extract one web source within an explicit allowlist, returning the content by digest with full provenance.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fweb-fetch\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M79A3C9NE99P24Q2QGG5236D","weather-forecast","Normalize provider weather evidence into an action-safe forecast packet with provenance, uncertainty, and stop conditions for downstream agents.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fweather-forecast\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M79A38RWEA5NHMYBQZPCVPQP","vuln-triage","Triage dependency or ecosystem vulnerability risk into remediation and advisory packets, grounding on verified CVE evidence when it is supplied.","https:\u002F\u002Fgithub.com\u002FZachDreamZ\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002FSKILL.md",[],[]]