Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kensaurus/cursor-kenji --skill audit-doctrinegit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kensaurus/cursor-kenji/audit-doctrine)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/audit-doctrine"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/audit-doctrine/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/audit-doctrine"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/audit-doctrine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.02035 |
| Opus 5.5 | $0.00024 | $0.00814 |
| Sonnet 5.5 | $0.00012 | $0.00407 |
| Haiku 4.5 | $0.00006 | $0.00203 |
Grade A, and why
audit-doctrine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audit-doctrine — Is the rule right, not merely enforced?
Degree of freedom: MIXED.
- Reference-practice comparison and remedy judgment (Phases 1–2): HIGH freedom — weigh each rule against how top products actually build.
- Governance-contract checks (Phases 3–4): LOW freedom — the contract's clauses are pass/fail; check each exactly.
Read-only. audit-gate-logic asks "can this gate be bypassed or
gamed?" — it assumes the rule is correct. This asks the harder
question: is the rule right on the merits? A ratchet that flawlessly
enforces bad doctrine is worse than no ratchet, because greenness
certifies the mistake and the developer, given only a codemod list,
restyles legitimate work to appease a regex instead of fixing a real
problem. An unexplained lint rejection erodes trust at that decision
point until people "adopt their own truth." This audit finds the rules
that are measuring taste, not correctness.
Present findings. Do not rewrite detectors, baselines, or tokens here.
This skill vs neighbors
| Skill | Owns |
|---|---|
| audit-doctrine (this) | Rule content — remedy, named token, Tier-D practice |
audit-gate-logic |
Rule machinery — bypass, gaming, required-but-not |
housekeep-gates |
Consolidate / delete duplicate gates (apply-now) |
enhance-arch-boundaries |
Install boundary enforcement, not judge doctrine |
housekeep-design |
Token/component SSOT — the sanctioned-form side |
docs-adr |
Record a justified divergence from Tier-D |
housekeep-backlog |
Un-remedied long-tail axes as BL- rows |
The governance contract
A custom rule/axis is sound only if all hold:
- Has a remedy — states the sanctioned alternative by name; a rule that only says "don't" is measuring taste.
- Sanctioned form is reachable — the approved pattern exists as a named token/class, not folklore the developer must reverse-engineer.
- Teaches on failure — the failure output prints the remedy AND
the offending
file:line, not just a codemod list. - Agrees with Tier-D reference practice — where the rule disagrees with how Stripe / Linear / GitHub / Docusaurus actually ship, the burden of proof is on the rule.
- Exceptions expire; baselines only shrink — no permanent
grandfather; the baseline cannot silently regrow (ratchet integrity
still belongs to
audit-gate-logic).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +3 lines · -7 tokens per session a73dffe1bd94
- 1mo ago First seen · 187 lines · 68 tokens per session scan A 16cf5575910a
audit-doctrine is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 26d ago), licensed MIT. It adds 61 tokens to every session and 2,035 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
code-review-codex
Final-gate code review via Codex CLI (codex-5.3, xhigh). Finds bugs, security issues, and regressions before commit. No edits — findings report only.
spec-review-codex
Audit project specs for conflicts, goal drift, ambiguity, and gaps via Codex CLI (gpt-5.2, xhigh). Read-only findings report.
codex-review
Run code reviews with the Codex CLI, prioritizing bugs, regressions, security risks, and missing tests. Use when the user asks for code review, PR review, diff review, or commit-range review via codex.
code-simplifier
Use after implementing features to simplify and refine code for clarity, consistency, and maintainability.
blind-spot-pass
Run a pre-build blind spot pass before the agent builds anything. Treat the user's prompt as the map and the real project as the territory: classify gaps across known knowns, known unknowns, unknown knowns, and unknown unknowns (with deps, edge cases, and blast radius under unknown unknowns); ask 5 to 10 high-leverage…
thermo-nuclear-code-quality-review
Extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use only when explicitly asked for a thermo-nuclear or thermonuclear code quality review, a deep code quality audit, or an especially harsh maintainability review.