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 | $0.00068 | $0.02000 |
| Opus 5 | $0.00034 | $0.01000 |
| Sonnet 5 | $0.00014 | $0.00400 |
| Haiku 4.5 | $0.00007 | $0.00200 |
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 5d 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 — 187 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.
- 5d 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 11d ago), licensed MIT. It adds 68 tokens to every session and 2,000 once invoked, about $0.0003 per session on Opus 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
refactor
Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
work-with-pr
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
tech-debt-audit
Thorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep, LSP, and language-native tooling. Produces TECHDEBTAUDIT.md with severity, effort estimates, and prioritized fixes. Use when asked for codebase health check, tech debt audit, architecture review, code quality assessment…