premise-check

Premise Check

A report that rests on evidence ends in an argument whose final conclusion answers the asker's questions. The writer lays it out so each step can be judged from the report alone; the checker judges every step and records why.

Standing rule: a format breach on an argument with at least one inference line is waivable on PASS and rewritten by the receiver; 0 inference lines or substantive defects require REVISE or FAIL and cannot pass or relay upward.

Writing the Report Argument

End the report with one fenced argdown block formatted per argdown-toulmin.

```argdown
===
asks:
  <ask_id>: <the asker's own words, one question>
answers:
  <ask_id>: <number of the line that answers it>
notes:
  a: <path:line, span id, task id, PR>
===

(1) <premise>. -- <basis phrase> ^a
(2) <premise quoting deciding value>. -- <basis phrase>
(3) <missing premise, written in>. -- assumed, not checked here
-- <warrant rule>. Unless: <defeater>; <ruled out by (n) | not ruled out | not tried>. --
(4) So, <qualifier bought by (3)>, <conclusion>.
```

Every peer message carries a fenced argdown block. A message making no claim (such as automated harness notices, /loop wakeups, or messages making no evidence-backed claims) carries the null form:

```argdown
===
asks: none
===

[no claim]
```

The null form clears the premise-check gate with no agent action. When an expected block is absent, the gate does not open: PASS is refused, and the receiver must return it for revision (REVISE "no argument supplied").

Basis Phrases (Closed Vocabulary)

Premise lines end with their basis in words, drawn strictly from this closed vocabulary:

Phrase	Rank	Meaning
I read it	3	Primary record, diff, log, or code read directly
I did it	3	Runtime command executed, test run, or artifact generated directly
attempted, failed	3	Direct reproduction attempt failed with observed error
rule	2	Framework axiom, project rule, or governing specification
worker reported, verdict	2	Another agent's report backed by a recorded verification ID
worker reported, unchecked	1	Peer writing or PKB note without a recorded verdict
assumed, not checked here	0	Unchecked assumption; requires a qualifier in its conclusion

Rules for the Block

1. The ask at the top: Copy the asker's exact words under its immutable ID (tg-<msg_id>, <task_id>/AC<n>).
2. Raw empirical observations: Premises with an observed basis (I did it, I read it, rank = 3) state raw empirical observations quoting deciding values inline (exit_code = 0, rank = 3, status: MERGED). They never state evaluative or generalising conclusions restating an acceptance criterion (such as "AC1 is met" or "behavior is correct"). Evaluative and generalising conclusions must sit below an inference bar as claims derived from those observations.
3. Numbered premises: Each line ends with -- <basis phrase>, with outside values quoted.
4. Pointers as lettered endnotes: Pointers live under notes: and are cited as ^a on the line.
5. The inference line: Starts --, ends --, on one line: warrant rule, then Unless: <defeater>; <status>.
6. Chain conclusions: Each step begins So and chains into subsequent steps.
7. Relay upward: Relaying a report upward requires its premise-check verdict; name the line each relayed sentence restates. Read claims against their source of record before relaying. Never relay an argument with 0 inference lines or substantive defects as fact.
8. Method pairing line: When an ask specifies a method, form, design, or value, the report carries a pairing line setting each specified feature beside what was done (e.g. @file -> @./at-test-target.md; read back -> Read tool), naming each departure with its reason, else departures: none. A detail in a method specification is load-bearing regardless of typography (quoted, backticked, or plain) unless the ask's purpose shows it free. Rewording that preserves the construct is not a departure; exact wording is not required where the construct is preserved.

Checking a Received Report or Direction

Directions

When an incoming direction arrives from another agent:

1. Verify that every instruction and requirement derives faithfully from ## Ask (or active user directives).
2. Refuse (REVISE) unverified caller method or template prescriptions before logging deliverables. A caller may pass only ## Ask (verbatim with ID), strategic fit/context, and the objective or skill invocation.
3. Once verified, log deliverables as a frozen ## Acceptance checklist on a PKB task before work starts.

Reports

Take observed premises with a pointer as given: never open a pointer or redo the work. A PKB node or peer writing ranks as worker reported, unchecked. Run four tests on every inference line:

Test	Passes when	Failure looks like
Valid	Premises meet every condition of the warrant; conclusion is no wider than premises; construct matches and sample is adequate; all specified methods, forms, designs, and values are paired and accounted for.	Missing condition; unruled defeater; scope drift (#scope-drift); construct mismatch or drift (#construct-drift: unnamed departure or silent substitution of specified method, form, design, or value); method gap (#method-gap: method cannot observe what is claimed); sample inadequacy (unexplained n=1 or n=2 probes asserted as proof of representative classes).
Supported	Each premise's basis can bear the step's stakes. Weakest premise bounds conclusion.	worker reported, unchecked or assumed on high-stakes step.
Answered	Final conclusion answers what each ask ID needs in substance.	Narrower conclusion; relayer acceptance items substituted for ask needs.
Sufficient	Proportionality holds: materiality, sufficiency (obvious, authority-backed, low-stakes), and necessity. A task's primary ask or acceptance criterion is never low-stakes or obvious.	Complex unbacked warrant on high-stakes step without decomposition; treating a primary ask or acceptance criterion as low-stakes or obvious.

Proportionality: accept warrants as stated when obvious, authority-backed (strictly limited to user words or governing spec), backed by a cited verdict, or cheap to reverse. A task's primary ask or acceptance criterion is never low-stakes or obvious. Send back for decomposition only when complex, unbacked, or high-stakes.

Fidelity Procedure

When checking an inference line or deliverable where the ask specifies a method, form, design, or value:

1. Extract specified features: Read ## Ask for any specified method, form, design, or value. Details in method specifications are load-bearing regardless of typography (quoted, backticked, or plain) unless the ask's purpose shows them free.
2. Check the pairing line: Verify the report pairs each specified feature with what was done.
3. Judge departures:
   • An unnamed departure (silent substitution of a specified method, form, design, or value) fails Valid with #construct-drift or #method-gap.
   • A block that silently swaps a specified form cannot PASS; return for revision (REVISE).
   • Rewording that preserves the construct and distinction passes; do not require verbatim wording outside specified forms or methods.

Recording the Verdict

• PASS: Every inference holds, every ask is answered, the weakest basis bears the stakes, and at least one inference line is tested (>= 1). Format-only defects on a substantively sound argument with >= 1 inference line are waived under Waived: and rewritten into standard form by the receiver before relaying upward.
• REVISE: Name the line, defect tag (#missing, #scope-drift, #conflict, #unanswered, #undercut, #construct-drift, #method-gap), and remedy. Mandatory for substantive defects or 0 inference lines (bare assertions); cannot be relayed upward as fact. Return to sender.
• FAIL: Conclusion does not answer the ask or contradicts evidence. Mandatory for substantive defects; cannot be relayed upward as fact.

Write the reason as the seven keyed lines:

Judged: <claim id>; asks <ask id>, <ask id>
Valid: (n) holds -- <rule and why it yields (n) here>
Supported: weakest <basis phrase> -- (<premise n>) <reason>
Answered: <ask id> ← (n)
Sufficient: (n) material; <obvious | authority-backed | low-stakes>; no objection
Waived: none | <format item> -- <justification>
Relay: "<sentence to relay>" ← (n) | none

For arguments with multiple inference lines, all yielded conclusions must be accounted for under Valid:--either via multiple Valid: lines, indented continuation lines, semicolon clauses ((n) holds -- ...; (m) holds -- ...), or grouped references ((n), (m) holds -- ... or (n) and (m) hold -- ...).

Format items: block, numbering, endnotes, basis wording, ask wording, layout.

Record the verdict:

uv run --project <plugin-dir> python <plugin-dir>/skills/premise-check/scripts/verdict.py --claim <claim_id> --verdict <PASS|REVISE|FAIL> --reason-file <path>

The recorder refuses a PASS whose reason misses a test line or ask ID, contradicts the block, or fails machine checks (syntax error, orphan statement, misaimed undercut); on refusal, actionable errors are emitted to stderr while keeping the gate armed.