Conciseness

The body is efficient — tight tables, a lean Quick Start, anti-patterns that each earn their place. Minor trimmable redundancy keeps it below 5: the three decisions are enumerated in the Overview and restated in the Core Workflow intro, and the three NOT-boundary paragraphs largely restate the frontmatter description. It is noticeably above the 3 anchor ('some unnecessary explanation') so 4 fits best.

Actionability

Fully executable, copy-paste-ready guidance: 'pip install "openagentontology[pq]"', a real bundled script invoked with realistic flags (--agent my-deploy-agent --operation deploy --target prod/api), runnable mint/verify one-liners with the expected output shown ('{'ok': True, 'sig_ok': True, ...}'), and a required-keys table that states exact failure behavior (exit 2 on missing keys). Matches the 5 anchor.

Workflow Clarity

The three decisions are clearly sequenced with real validation checkpoints: the manifest is validated before signing (rejected with exit 2), and verification recomputes the hash and checks each signature leg, returning ok/hash_ok/sig_ok. It falls short of the 5 anchor because there is no explicit error-recovery loop (what to do when mint or verify fails) — squarely the 4 anchor ('clear sequence with most checkpoints; minor validation gaps').

Progressive Disclosure

A 102-line overview body with one clearly signaled, one-level-deep reference — 'See [references/receipt-fields.md](references/receipt-fields.md) for the full receipt schema and the post-quantum rationale' — and the receipt-schema bulk correctly lives in that file, which exists in the bundle alongside the real scripts/build_action_manifest.py. Matches the 5 anchor (clear overview, well-signaled one-level-deep references, easy navigation).

Specificity

The description lists multiple concrete actions — mint a tamper-evident, post-quantum-signed receipt, verify it 'from the certificate alone', and the three explicit decisions (whether needed, minting, verifying) — with concrete action types (deploy, delete, pay, grant-access, model decision). Coverage within the niche is comprehensive, including the delegation of signing to OpenAgentOntology, matching the 5 anchor rather than the 4 anchor's 'minor gaps'.

Completeness

Both what and when are explicit: 'Mint a tamper-evident, post-quantum-signed receipt... so it can be verified later from the certificate alone' and 'Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping'. This matches the 5 anchor (explicit what AND when with concrete trigger phrases).

Trigger Term Quality

Good natural-term coverage: 'receipt', 'tamper-evident', 'post-quantum', 'deploy, delete, pay, grant-access', 'EU AI Act Article 12 record-keeping', 'proven later'. A few natural phrasings a user might say are absent (e.g. 'audit trail', 'accountability', 'provenance'), which fits the 4 anchor ('good keyword coverage; a few natural terms missing') better than the 5 anchor's comprehensive synonym coverage.

Distinctiveness Conflict Risk

A clear niche (signed evidence receipts for consequential agent actions) with explicit negative boundaries — 'Not after-the-fact log analysis; not a hosted notary; not a legal opinion' — that sharply reduce overlap with logging, notary, and legal-advice skills. Minimal conflict risk, matching the 5 anchor.