self-audit-tools

self-audit-tools is a skill for Claude Code, Codex from omnigentx/jarvis. It costs 79 tokens per session (4,946 once invoked), scanned A, original, MIT.

A procedure for checking the tools visible to an AI agent and reporting what they can and cannot verify. It separates the agent being audited from the person coordinating the audit.

In plain words
What is it for?
Use it when an agent must audit its own tools or when a coordinator needs to combine self-audit reports without treating them as independent verification.
Why use it?
It prevents claims about tools, call counts, or other agents’ capabilities that the reviewer cannot actually confirm.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when an agent must audit its own tools or when a coordinator needs to combine self-audit reports without treating them as independent verification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/omnigentx/jarvis/self-audit-tools
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 omnigentx/jarvis --skill self-audit-tools
Clone the repo
git clone --depth 1 https://github.com/omnigentx/jarvis

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 self-audit-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/omnigentx/jarvis/self-audit-tools.svg)](https://agentmods.dev/skills/omnigentx/jarvis/self-audit-tools)
Your own site
<a href="https://agentmods.dev/skills/omnigentx/jarvis/self-audit-tools"><img src="https://agentmods.dev/badge/skills/omnigentx/jarvis/self-audit-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,946 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 112
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
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 $0.00079 $0.04946
Opus 5 $0.00039 $0.02473
Sonnet 5 $0.00016 $0.00989
Haiku 4.5 $0.00008 $0.00495

Measured 7d ago against content hash e28e4f00e393, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

self-audit-tools 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 7d 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.

backend/.fast-agent/skills/self-audit-tools/SKILL.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Audit Tools Skill

When a task asks you to audit your own toolset, follow this protocol exactly. This skill is the single source of truth for self-audit; the task brief will not duplicate these rules, so read this in full before acting.

Capability honesty — read this first

This skill is written around what each role can actually observe:

Role Can observe Cannot observe
Member (audit subject) Own tool catalog, own tool-call results, own message history Other members' tools, other members' message history
Aggregator (orchestrator / PM) Emails received, meeting transcripts, agent_spawner__get_team_status (high-level state per member) AND its own toolset Members' tool catalogs, members' tool-call counts, anything not explicitly emailed or said in a meeting
Requester (Jarvis / user) Whatever the aggregator delivers Same blind spots as the aggregator

That table is load-bearing. Rules below honour it — the aggregator never "verifies counts" of another member because it cannot. The aggregator only checks what is plainly present in the text it receives.

Which role are you?

Answer this first, in your own head, before reading further:

  • No team around you (solo spawn, no PM, no peers in roster). You are a standalone member. Run Part A and email the report to the requester named in your context (Jarvis / parent agent). Part B does not apply.
  • You are a team member (BA / SA / Dev / Designer / QE / DSO / etc., with a PM in your roster). Run Part A and email your report to the PM. Do not run Part B — only the orchestrator aggregates.
  • You are the orchestrator (PM, role tagged orchestrator in the template, or first spawned by spawn_team_tool). Run both parts: Part A for your own toolset (no email — you are the recipient), then Part B to collect member emails and produce the combined roll-up that interleaves your own audit with theirs.

Re-read the table above and the bullet list whenever you forget which half of the skill applies to you.

Read the full file on GitHub · 440 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. 7d ago First seen · 440 lines · 79 tokens per session scan A e28e4f00e393

Subscribe to this mod's changes

self-audit-tools is a skill published in the GitHub repository omnigentx/jarvis (36 stars, last pushed 11d ago), licensed MIT. It adds 79 tokens to every session and 4,946 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens