audit-light

audit-light is a skill for Claude Code from HAX-Studio/mnemonica. It costs 68 tokens per session (1,475 once invoked), scanned A, original, MIT.

A quick Git-based documentation check for Mnemonica projects. Mnemonica is a system that keeps project knowledge in documentation files, and this skill compares those files with changes since a saved checkpoint.

In plain words
What is it for?
Use it after recent commits to check whether the project's documentation is still in sync. It requires a Git repository and is started by the user.
Why use it?
It catches recent code changes that are missing from the project's knowledge documents without rereading the entire project.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the mnemonica plugin — 8 skills shipped together

Good fit Use it after recent commits to check whether the project's documentation is still in sync. It requires a Git repository and is started by the user.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add HAX-Studio/mnemonica
Claude Code
/plugin install mnemonica

Made for: Claude Code.

Or install mnemonica, the plugin that ships this one along with the rest of its 8 skills.

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-light

README.md
[![agentmods](https://agentmods.dev/badge/skills/hax-studio/mnemonica/audit-light.svg)](https://agentmods.dev/skills/hax-studio/mnemonica/audit-light)
Your own site
<a href="https://agentmods.dev/skills/hax-studio/mnemonica/audit-light"><img src="https://agentmods.dev/badge/skills/hax-studio/mnemonica/audit-light.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,475 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00068 $0.01475
Opus 5 $0.00034 $0.00737
Sonnet 5 $0.00014 $0.00295
Haiku 4.5 $0.00007 $0.00147

Measured 8d ago against content hash f57c329594de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

audit-light 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/diff-since-checkpoint.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-light/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mnemonica: audit-light

Reconcile knowledge/ with only what changed since the last checkpoint — a cheap, targeted pass, not a full rescan. Read ${CLAUDE_PLUGIN_ROOT}/references/knowledge-conventions.md first; it defines the checkpoint file format, the module index format, and the update/cross-cutting rules this skill applies. This skill requires git (it has no concept of "since the last checkpoint" without commit history) and is always invoked directly by the user — never by a hook, and never automatically on commit or push.

If the user's invocation includes extra wording beyond the trigger phrase, treat it as scoping or preference for this run — for example, pointing out a companion tool to also consult, or which module they especially care about. It cannot skip the escalation in Step 3 when the diff is too broad, and it cannot make the checkpoint advance when this skill would otherwise not advance it.

Step 1: Get the change range

Run ${CLAUDE_PLUGIN_ROOT}/skills/audit-light/scripts/diff-since-checkpoint.sh <project-root>.

  • Exit 5 (NO_GIT_REPO): this project has no git repository. Tell the user audit-light needs git and cannot run here; suggest git init (no remote required) if they want incremental audits, and stop.
  • Exit 2 (NO_CHECKPOINT): there is no baseline to diff from yet. Tell the user to run mnemonica:audit-full first — it creates the checkpoint as part of its own run — and stop.
  • Exit 3 (STALE_CHECKPOINT): the recorded commit is not an ancestor of HEAD anymore (rebase, squash, or history rewrite — note that the old commit can still physically exist in the repository for a long time after this happens, so this is a real ancestry check, not a mere existence check). Tell the user the checkpoint is stale and recommend mnemonica:audit-full to re-baseline, and stop.
  • Exit 4 (CORRUPT_CHECKPOINT): the state file exists but couldn't be parsed. This should not happen through normal use (the checkpoint is always written by scripts/write-checkpoint.sh), so treat it as a sign the file was hand-edited. Recommend mnemonica:audit-full to re-baseline, and stop.
  • Success: the script prints the commit range, the new HEAD SHA, and the list of files changed across that range.

Read the full file on GitHub · 104 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 104 lines · 68 tokens per session scan A f57c329594de

Subscribe to this mod's changes

audit-light is a skill published in the GitHub repository HAX-Studio/mnemonica (3 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,475 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

precommit

Pre-commit checks — lint:fix -> build -> test.

sd0xdev/sd0x-harness · 15 tokens

next-step

Change-aware next step advisor. Use when: user asks what to do next, workflow progression is unclear, session just started with dirty worktree. Not for: executing the suggested command (user decides), auto-loop decisions (hooks handle that). Output: findings-based suggestions or session summary with commit seed.

sd0xdev/sd0x-harness · 63 tokens

precommit-fast

Quick pre-commit checks — lint:fix -> test.

sd0xdev/sd0x-harness · 15 tokens

commit

Changelog and commit — lightweight motion for day-to-day plugin dev work in the monorepo. One commit per plugin scope; CHANGELOG and staging routed by detected slug. Trigger when the user says "commit", "commit this", "save this", "wrap this up", "let's commit", or finishes a change and wants to capture it. NOT for…

gtapps/claude-code-hermit · 90 tokens

git-commit

Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.

fvadicamo/dev-agent-skills · 49 tokens

smart-commit

Smart batch commit. Analyzes uncommitted changes, groups by cohesion, generates commit messages matching project style. Default: output git commands for manual execution. With --execute: directly run git add + git commit (requires user approval). Use when: user says 'commit', 'batch commit', 'prepare commit', 'write…

sd0xdev/sd0x-harness · 78 tokens