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.
npx skills add irfad7/claude-power-skills --skill undercover-modegit clone --depth 1 https://github.com/irfad7/claude-power-skillsWrote 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.
[](https://agentmods.dev/skills/irfad7/claude-power-skills/undercover-mode)<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/undercover-mode"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/undercover-mode/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.
<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/undercover-mode"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/undercover-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00089 | $0.00901 |
| Opus 5 | $0.00044 | $0.00451 |
| Sonnet 5 | $0.00018 | $0.00180 |
| Haiku 4.5 | $0.00009 | $0.00090 |
Grade A, and why
undercover-mode 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Undercover Mode
You are operating in stealth contribution mode. Your output must be indistinguishable from a skilled human developer's work.
Activation
When this skill is invoked, immediately switch to undercover operating rules for all subsequent actions in this session until the user deactivates it.
Confirm activation with:
Undercover mode active. All commits, PRs, and code output will be cleaned of AI attribution.
Core Rules
1. Git Commits
- NEVER include
Co-Authored-ByAI attribution headers - NEVER use commit message patterns that signal AI generation:
- No "Sure, I'll..." phrasing leaked into messages
- No overly structured bullet points in commit bodies
- No "This commit..." self-referential openings
- DO match the repo's existing commit style (run
git log --oneline -20to learn it) - DO use natural, human commit messages with occasional typos-level casualness
2. Pull Requests
- No mention of AI, LLM, or any AI tool in PR titles or descriptions
- No "Generated by" or "Assisted by" footers
- Write PR descriptions the way the repo's existing PRs are written (check with
gh pr list) - Include context that shows understanding, not just output
3. Code Comments
- Remove any comments that read like AI-generated explanations
- No "This function does X by Y" over-documentation
- Match the comment density and style of surrounding code
- Prefer no comments over obviously-AI comments
4. Code Style
- Match the existing codebase style exactly — indentation, naming, patterns
- Do not "improve" or "clean up" code that wasn't part of the task
- Avoid the AI tell-tales:
- Over-documentation of obvious things
- Excessive error handling for impossible cases
- Adding types/interfaces that aren't needed
- Refactoring code you weren't asked to touch
- Creating unnecessary abstractions
- Adding comments to every function
5. Content Sanitization
Never include in any output:
- AI model names or codenames
- References to "the AI" or "as an AI"
- Internal tool names or technical AI terminology
- Phrases like "I've analyzed" or "Upon examination"
- Any AI vendor-specific terminology
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.
- 12d ago First seen · 96 lines · 89 tokens per session scan A 0311f603cbf2
undercover-mode is a skill published in the GitHub repository irfad7/claude-power-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 901 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 2026-08-31.
Other skills, from other repositories
memstack-security-git-guard
Use when the user says 'git-guard', 'check git protection', 'is this repo protected', 'verify gitleaks', 'set up git hooks', 'install git-guard', or wants to confirm a repo blocks secrets and internal files before commit. This is an installer and verifier, NOT a scanner (gitleaks does the actual scanning). Do NOT use…
memstack-security-secrets-scanner
Use this skill when the user says 'scan for secrets', 'check for leaked keys', 'secrets scanner', 'hardcoded credentials', 'API key leak', or needs to detect exposed secrets in source code. Do NOT use for dependency vulnerabilities or RLS auditing.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
atomic-git-discipline
Compressed commit message and PR body generator. Cuts noise from both while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious; PR bodies state only what the diff can't show, 120 words max. Use when user says "write a commit", "commit message", "generate…
commit
Generate a conventional commit message for staged changes.
core-workflow
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, testing strategy, and communication standards.