What is system-audit?

A health check for an AI assistant's own project setup, including its agents, hooks, skills, settings, memory, and vault folders.

Checking whether the assistant's configuration is complete after setup or customization, including agent metadata, hook files, skills, JSON settings, memory links, and vault folders.

It finds missing files, unfinished setup placeholders, invalid configuration, broken links, and inconsistent module structure before they cause problems.

system-audit — Skill for Claude Code and Codex by chacosoldier: A health check for an AI assistant's own project…

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/chacosoldier/compabob/system-audit

Any agent

npx skills add chacosoldier/compabob --skill system-audit

Clone the repo

git clone --depth 1 https://github.com/chacosoldier/compabob

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chacosoldier/compabob/system-audit.svg)](https://agentmods.dev/skills/chacosoldier/compabob/system-audit)

Your own site

<a href="https://agentmods.dev/skills/chacosoldier/compabob/system-audit"><img src="https://agentmods.dev/badge/skills/chacosoldier/compabob/system-audit.svg" alt="Measured on agentmods" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 426 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.

Model	Per session	Once invoked
Fable 5	$0.00046	$0.00426
Opus 5	$0.00023	$0.00213
Sonnet 5	$0.00009	$0.00085
Haiku 4.5	$0.00005	$0.00043

Measured 5d ago against content hash 5f462528362f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

system-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 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.

.claude/skills/system-audit/SKILL.md · 24 lines

What it actually says

System Audit

Verify the assistant's own configuration is intact and consistent. Run it after customizing the kit, or any time something feels off.

Checks

Setup complete. Search the repo for unfilled placeholders, the pattern setup.sh fills (double braces around capitals, e.g. the assistant-name token). Any hit outside docs/ or a .template file means setup did not finish. Report each one.
Agents. Every file in .claude/agents/ (except _-prefixed ones) has valid frontmatter with name, description, and tools. The description says when to use the agent. Flag any agent with an empty or vague description (routing will suffer).
Hooks. Every hook referenced in .claude/settings.json exists on disk. Run bash scripts/init.sh and report its result.
Skills. Every directory in .claude/skills/ has a SKILL.md with name and description frontmatter.
Settings. .claude/settings.json is valid JSON. settings.local.json exists (created by setup.sh).
Memory. memory/MEMORY.md exists and its links into memory/topics/ resolve.
Vault. vault/ has the expected folders and vault/00-Home.md exists.
Modules. For each enabled module, its own check passes (see the module's README).

Output

A short verdict first: all green, or N issues. Then a checklist with PASS / WARN / FAIL per item, and for each FAIL the concrete fix. End with the single most important thing to fix, if anything.

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.

5d ago First seen · 24 lines · 46 tokens per session scan A 5f462528362f

Subscribe to this mod's changes

system-audit is a skill published in the GitHub repository chacosoldier/compabob (32 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 426 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 2026-08-30.

ai-agents ai-assistant anthropic automation claude claude-code

system-audit

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

System Audit

Checks

Output

What this file has done since we first saw it

Other skills, from other repositories

agent-release-swarm

agent-code-analyzer

add-resend

add-macos-statusbar

git-commit

excel-basic-statistics-and-routing