system-prompt-audit

system-prompt-audit is a skill for Claude Code, Codex from strikersam/autonomous-ai-agency. It costs 0 tokens per session (602 once invoked), scanned A, original, MIT.

A review of system-level instructions stored in a repository’s Claude configuration, including agents, skills, commands, and CLAUDE.md. It records their contents and checks them for conflicts, gaps, and safety problems.

In plain words
What is it for?
Use it before changing the .claude directory, adding an agent or skill, preparing a release, or running a governance review.
Why use it?
It makes hidden operating rules easier to inspect and can reveal duplicate roles or contradictory instructions before they cause inconsistent behaviour.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; installed under .agents/ (shared by several agents).

Good fit Use it before changing the .claude directory, adding an agent or skill, preparing a release, or running a governance review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/strikersam/autonomous-ai-agency/system-prompt-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 strikersam/autonomous-ai-agency --skill system-prompt-audit
Clone the repo
git clone --depth 1 https://github.com/strikersam/autonomous-ai-agency

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 system-prompt-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/system-prompt-audit/github.svg)](https://agentmods.dev/skills/strikersam/autonomous-ai-agency/system-prompt-audit)
Your own site
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/system-prompt-audit"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/system-prompt-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 system-prompt-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/system-prompt-audit"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/system-prompt-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 602 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 pass 7 Sept 2026
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 $0.00000 $0.00602
Opus 5 $0.00000 $0.00301
Sonnet 5 $0.00000 $0.00120
Haiku 4.5 $0.00000 $0.00060

Measured 12d ago against content hash 5b65c2715ed7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

system-prompt-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 12d 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.

.agents/skills/system-prompt-audit/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: system-prompt-audit

Purpose

Audit all system-level instructions embedded in this repository's Claude configuration, surface them as a structured inventory, and validate them for consistency, safety, and alignment with project goals.

Inspired by CL4R1T4S (Latin: "clarity") — the open-source project that collects and publishes AI system prompts to promote transparency.

When to Use

  • Run before merging changes to .claude/ directory
  • Run as part of release readiness checks
  • Run when a new agent or skill is added
  • Run on-demand for governance audits

Steps

1. Inventory Collection

Scan the following paths:
  .claude/agents/       → agent persona definitions
  .claude/skills/       → skill behavioral specs
  .claude/commands/     → command implementations
  CLAUDE.md             → root-level project instructions

For each file, record:

  • File path
  • Word count (proxy for complexity)
  • Presence of: role definition, constraints, examples, output format

2. Consistency Check

Cross-reference all files for:

  • Duplicate roles: two agents claiming the same responsibility
  • Contradictory constraints: one skill allows X, another forbids X
  • Missing output formats: skills that don't specify what they produce
  • Undocumented side effects: skills that write files/commit without stating so

3. Safety Check

Flag any instructions that:

  • Allow unrestricted file system writes
  • Allow network calls without validation
  • Grant escalated permissions
  • Lack human-in-the-loop checkpoints for destructive operations

4. Generate Audit Report

Write docs/system-prompt-audit.md with:

# System Prompt Audit Report
Generated: <timestamp>

## Summary
- Total components audited: N
- Agents: N | Skills: N | Commands: N
- Issues found: N (critical: N, warnings: N, info: N)

## Inventory Table
| Component | Type | Role | Has Constraints | Has Examples |
|-----------|------|------|-----------------|--------------|

## Issues
### Critical
...
### Warnings
...
### Info
...

## Full Behavioral Inventory
[per-component breakdown]

Read the full file on GitHub · 90 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. 12d ago First seen · 90 lines · 0 tokens per session scan A 5b65c2715ed7

Subscribe to this mod's changes

system-prompt-audit is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 602 tokens. 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

assimilate-popular-workflows

This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…

a5c-ai/babysitter · 110 tokens

process-builder

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

a5c-ai/babysitter · 32 tokens

mcp-app-verification

Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.

a5c-ai/babysitter · 48 tokens

guardrails-ai-setup

Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.

a5c-ai/babysitter · 30 tokens

mcp-app-scaffolding

Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.

a5c-ai/babysitter · 50 tokens

mcp-csp-investigation

Comprehensive Content Security Policy audit for MCP Apps in sandboxed iframes. Discovers all network origins, traces them to source, and generates CSP configuration for registerAppResource.

a5c-ai/babysitter · 43 tokens