atlas-audit

atlas-audit is a skill for Claude Code, Codex from madaeroblade/atlas. It costs 33 tokens per session (430 once invoked), scanned A, original, MIT.

A repository review tool for Atlas, the project knowledge system used by coding agents.

In plain words
What is it for?
It audits Atlas against the repository, reports findings, and can repair Atlas files and graph data without changing application source code.
Why use it?
It finds outdated, duplicated, contradictory, oversized, or incorrectly linked project knowledge before it misleads the agent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit It audits Atlas against the repository, reports findings, and can repair Atlas files and graph data without changing application source code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/madaeroblade/atlas/atlas-audit
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.

Any agent
npx skills add madaeroblade/atlas --skill atlas-audit
Clone the repo
git clone --depth 1 https://github.com/madaeroblade/atlas

Made for: Claude Code, Codex.

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 atlas-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/madaeroblade/atlas/atlas-audit/github.svg)](https://agentmods.dev/skills/madaeroblade/atlas/atlas-audit)
Your own site
<a href="https://agentmods.dev/skills/madaeroblade/atlas/atlas-audit"><img src="https://agentmods.dev/badge/skills/madaeroblade/atlas/atlas-audit/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.

agentmods 80×15 button for atlas-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/madaeroblade/atlas/atlas-audit"><img src="https://agentmods.dev/badge/skills/madaeroblade/atlas/atlas-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 430 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 $0.00033 $0.00430
Opus 5 $0.00016 $0.00215
Sonnet 5 $0.00007 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured 10d ago against content hash 8028c419c9f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

atlas-audit 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 10d 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.

adapters/claude/skills/atlas-audit/SKILL.md · 75 lines

What it actually says

Atlas Audit

Resolve Atlas

Read and follow:

  1. $ATLAS_ROOT/engine/audit/ENGINE.md
  2. $ATLAS_ROOT/engine/audit/HEALTH.md

If .atlas/ does not exist, report that Atlas is not initialized.

Phase separation

Perform the audit in two stages.

Stage 1 — Read-only audit

Inspect Atlas and relevant repository evidence.

Produce findings before making repairs.

Stage 2 — Repair

After the findings are established, repair Atlas according to the Audit Engine.

Do not modify application source code.

Re-derive, do not re-read

Stage 1 is not a proofread. Every count, table sum, enumeration, cited command and path:line reference in Atlas must be recomputed against the repository.

A wrong number reads exactly like a right one, and no other check catches it.

Repair scope

Allowed Atlas repairs include:

  • stale canonical knowledge;
  • a GRAPH.yaml below the current schema version — migrate it;
  • wrong counts, sums and citations;
  • invalid paths;
  • graph relationships;
  • registers mistyped as nodes;
  • a GRAPH.yaml over budget;
  • knowledge duplicated into the always-loaded CLAUDE.md;
  • obsolete observations;
  • duplicated facts;
  • bloated documents;
  • benchmark scenarios with .atlas/ provenance;
  • benchmark coverage metadata.

Do not rewrite healthy knowledge for style alone.

Completion

Report:

  • health findings by severity;
  • health score (out of 16);
  • every count or citation that failed re-derivation, even where the surrounding claim was correct;
  • routing cost in bytes — GRAPH.yaml, INDEX.md, CLAUDE.md — and whether it grew;
  • repairs made;
  • knowledge removed/merged;
  • graph changes;
  • benchmark coverage gaps and INVALID scenarios;
  • unresolved uncertainties.
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. 10d ago First seen · 75 lines · 33 tokens per session scan A 8028c419c9f3

Subscribe to this mod's changes

atlas-audit is a skill published in the GitHub repository madaeroblade/atlas (2 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 430 once invoked, about $0.0002 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

mem0-status

Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.

mem0ai/mem0 · 44 tokens

inspector-workbench

Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…

CopilotKit/CopilotKit · 112 tokens

md-audit

Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…

chaitanyagiri/munder-difflin · 85 tokens

potpie-debug-memory

Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.

potpie-ai/potpie · 41 tokens

browserwing-admin

Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.

MemTensor/MemOS · 47 tokens

exploiting-format-string-vulnerabilities

Methodology for exploiting format string bugs where attacker-controlled data reaches the format argument of printf-family functions, enabling stack/memory disclosure (info leaks for ASLR/PIE/canary defeat) and arbitrary write primitives (%n) to hijack control flow via GOT/.finiarray overwrites.

xalgorix/xalgorix · 69 tokens