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 darkroomengineering/cc-settings --skill poke-holesgit clone --depth 1 https://github.com/darkroomengineering/cc-settingsWrote 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/darkroomengineering/cc-settings/poke-holes)<a href="https://agentmods.dev/skills/darkroomengineering/cc-settings/poke-holes"><img src="https://agentmods.dev/badge/skills/darkroomengineering/cc-settings/poke-holes/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/darkroomengineering/cc-settings/poke-holes"><img src="https://agentmods.dev/badge/skills/darkroomengineering/cc-settings/poke-holes.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 | $0.00044 | $0.01845 |
| Opus 5.5 | $0.00018 | $0.00738 |
| Sonnet 5.5 | $0.00009 | $0.00369 |
| Haiku 4.5 | $0.00004 | $0.00185 |
Grade A, and why
poke-holes 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 4d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Verification
Standalone Codex
Create each fresh panelist with spawn_agent,
deliver context while it runs with send_message, trigger another turn once it
is idle with followup_task, wait with wait_agent, and stop its current turn
with interrupt_agent only when necessary. Never spawn codex-verifier and
never run codex-run.ts from inside Codex.
Only read-only reviewers may overlap. Writers share the working tree unless the live host explicitly offers isolation, so any implementer and test-writer follow-up must use non-overlapping ownership and run serially.
When to Use
- Security-sensitive code (auth, crypto, permissions)
- Data integrity (migrations, schema changes, ETL)
- Financial logic (payments, billing, calculations)
- Breaking changes (API contracts, public interfaces)
The Three-Agent Pattern
Agent 1: Finder
Agent(reviewer, "You are a bug finder. Analyze the following code/changes thoroughly.
Score yourself: +1 for low-impact issues, +5 for medium-impact, +10 for critical.
Report every potential issue you find — edge cases, race conditions, missing validation,
security holes, logic errors, performance problems.
Report your total score at the end.
Target: [describe what to verify]
Files: [list files]")
Finder over-reports by design — this is the superset of all possible issues.
Standalone Codex panel
Use three separate native agents instead of the Claude bridge: spawn a fresh issue-finder, wait until it finishes, pass its report to a separate disprover, then wait until that agent finishes before spawning the judge with both reports. Follow the lifecycle above for each role. Skip the Claude cross-model finder below.
Cross-model finder (when the Codex bridge is available)
All three agents here are Claude — one model family with shared blind spots, which is the exact self-preferential bias this skill exists to fight. When the Codex bridge is available, add a non-Claude voice to the panel by running, in parallel with Agent 1:
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.
- 4d ago Changed · -7 lines 1a0fc0a8e334
- 13d ago Changed · +15 lines b7e06d4c6eec
- 18d ago First seen · 189 lines · 44 tokens per session scan A 0fa5ca18308e
poke-holes is a skill published in the GitHub repository darkroomengineering/cc-settings (52 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,845 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
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…
resolve-review-pr
Review an existing fix PR using the audited repro and full diff, preserving branch and approval rules.
oracle
Oracle second-model review: bundle prompts/files, debug, refactor, design.
brutal-honesty-review
Unvarnished technical criticism combining Linus Torvalds' precision, Gordon Ramsay's standards, and James Bach's BS-detection. Use when code/tests need harsh reality checks, certification schemes smell fishy, or technical decisions lack rigor. No sugar-coating, just surgical truth about what's broken and why.
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…