audit-rules

audit-rules is a skill for Claude Code, Codex from fullymiddleaged/Clawness. It costs 65 tokens per session (1,266 once invoked), scanned A, original, MIT.

A maintenance skill that reviews one area of the Clawness rule collection against current official documentation. It records which versions and sources each rule was checked against without rewriting the rule text.

In plain words
What is it for?
Use it to audit one rule domain at a time. It reports measurable issues, verifies whether rules are still accurate, and writes an individual record of the applicable versions, verification date, and sources.
Why use it?
It helps maintainers find outdated, duplicate, unreachable, or weakly supported rules. Per-rule version and source stamps make it clear what evidence supports each review.

Skill for Claude CodeCodex

Part of the clawness plugin — 13 skills, 7 agents shipped together

Install

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.

agentmods
npx agentmods add skills/fullymiddleaged/clawness/audit-rules
Any agent
npx skills add fullymiddleaged/Clawness --skill audit-rules
Clone the repo
git clone --depth 1 https://github.com/fullymiddleaged/Clawness

Made for: Claude Code, Codex.

Or install clawness, the plugin that ships this one along with the rest of its 13 skills, 7 agents.

Wrote 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.

agentmods badge for audit-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/fullymiddleaged/clawness/audit-rules.svg)](https://agentmods.dev/skills/fullymiddleaged/clawness/audit-rules)
Your own site
<a href="https://agentmods.dev/skills/fullymiddleaged/clawness/audit-rules"><img src="https://agentmods.dev/badge/skills/fullymiddleaged/clawness/audit-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,266 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00065 $0.01266
Opus 5 $0.00032 $0.00633
Sonnet 5 $0.00013 $0.00253
Haiku 4.5 $0.00006 $0.00127

Measured 3d ago against content hash 2360c8c27aff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-rules 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 3d 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.

skills/audit-rules/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit a rule domain

clawness audit-rules measures what is measurable — missing provenance, eval blind spots, near-duplicate rules, unreachable rules. This skill is the half that isn't measurable: is this rule still true?

It is also where version ranges come from. There is no way to derive what a rule was written against — git dates are a weak proxy (an author can write for an older major than the day's current one) and rule text names an API, not a version. So applies_to is an output of this review, established rule by rule from that rule's own evidence.

One domain per run. 212 rules in one pass is not a review. Reviewing several domains at once is how a careful pass becomes a bulk stamp, which is the exact failure per-rule stamping exists to prevent.

Before you start

Run the mechanical checks first, so the review has the numbers in front of it:

The clawness CLI ships with the plugin but isn't on your PATH; run it via the wrapper the SessionStart bootstrap writes each session (editable/manual installs may use python -m clawness.cli instead):

CLAW="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/clawness/clawness-cli.sh"
bash "$CLAW" audit-rules --stale --overlap

--overlap matters here specifically: near-duplicates within the domain you are about to review are cheapest to spot while you have all of it in your head.

Steps

1. Read the whole domain

Every rules/<domain>/*.yml, plus any existing applies_to on them. Note which frameworks the domain names and what versions the current rules imply.

2. Look up what is current

Follow the lookup procedure in skills/refresh/SKILL.md step 3 — same procedure, different destination: that one writes to one project's .clawness/rules/, this one fixes the corpus upstream. In short: the framework's own migration guide, then its changelog, then the current official docs page. Not recalled knowledge — a model's sense of "what's current" lags real releases by exactly the gap this feature exists to close.

Read the full file on GitHub · 125 lines

Changes

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.

  1. 3d ago First seen · 125 lines · 65 tokens per session scan A 2360c8c27aff

Subscribe to this mod's changes

audit-rules is a skill published in the GitHub repository fullymiddleaged/Clawness (3 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 1,266 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 2026-08-31.

Related

Other skills, from other repositories

linked-intent-dev

Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…

jszmajda/lid · 87 tokens

update-lid

Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…

jszmajda/lid · 105 tokens

arrow-maintenance

Navigation and audit overlay for linked-intent development. Use when working with docs/arrows/ — orienting via index.yaml, auditing spec-to-code coherence, detecting reverse orphans and drift, splitting/merging/renaming/re-parenting segments. Dual-mode: ambient guidance when the overlay is present…

jszmajda/lid · 85 tokens

map-codebase

Bootstrap LID in an existing (brownfield) codebase. Deep-reads every file in the declared scope, offers lens-based clustering options, generates skeleton LLDs/HLD/EARS bottom-up, then creates arrow docs and prompts the user to flesh out the skeletons. Token-intensive by design. Use when asked to map a codebase…

jszmajda/lid · 92 tokens

bidirectional-differential

Audit coherence across an arrow of intent by running two parallel fresh Claude sessions — one reconstructs code from a single EARS, the other reconstructs the EARS from stripped code — then classifies the drift between them. Use when the user invokes /differential-audit, asks to audit EARS-to-code drift for a feature…

jszmajda/lid · 172 tokens

lid-coach

Review a project's current linked-intent-development (LID) usage against LID's own principles and produce a prioritized report of recommendations for getting more out of the methodology. Invoke when the user runs /lid-coach, asks for a LID review, asks how they could use LID better, wants feedback on their LID setup…

jszmajda/lid · 117 tokens