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 brcampidelli/chimera-agent --skill pin-the-case-that-narrowed-the-rulegit clone --depth 1 https://github.com/brcampidelli/chimera-agentWrote 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/brcampidelli/chimera-agent/pin-the-case-that-narrowed-the-rule)<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/pin-the-case-that-narrowed-the-rule"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/pin-the-case-that-narrowed-the-rule/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/brcampidelli/chimera-agent/pin-the-case-that-narrowed-the-rule"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/pin-the-case-that-narrowed-the-rule.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00567 |
| Opus 5 | $0.00022 | $0.00283 |
| Sonnet 5 | $0.00009 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
pin-the-case-that-narrowed-the-rule 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.
What it actually says
Trigger
A check you wrote has failed on something that is actually fine, and you are about to add an exemption, an allowlist entry, or a narrower pattern.
It does not apply when the check found a real problem — fix the problem. It also does not apply to tuning a threshold before the check has ever run in anger.
Do
- Write down, in one sentence, why the flagged case is legitimate. If you cannot, the check may be right and the code wrong.
- Add both cases to the test suite: the legitimate one that must pass, and a synthetic version of the real violation that must still fail.
- Narrow the rule as little as possible. Exempt a path, not a whole directory; require a negation nearby, rather than deleting the phrase from the list.
- Put the narrowing in its own commit, and say in the message which case forced it.
Avoid
Deleting the rule because it was annoying once. Also avoid the quieter version: broadening an exemption until the rule covers nothing — an allowlist that grows every sprint is a rule being retired one line at a time, without anyone deciding to retire it.
Avoid exempting by file when the real distinction is by meaning. A phrase check that bans a sentence outright will ban the warning that negates it, and the honest fix is to require the negation, not to stop checking that page.
Check
After narrowing, run the suite with the original violation reintroduced. It must still fail.
Then read the diff of the rule itself and ask: what class of problem can now get through that could not before? If you cannot answer, the narrowing was not understood.
Risk
This adds a test for every exception, and a suite full of exception tests is a suite that is tedious to read.
The bigger risk is treating the pinned test as proof the rule is still strong. It proves one case still fails. A rule narrowed five times has five pinned cases and possibly a large hole between them, and only re-reading the rule as a whole will show that.
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 · 61 lines · 44 tokens per session scan A 9ae6da37eebf
pin-the-case-that-narrowed-the-rule is a skill published in the GitHub repository brcampidelli/chimera-agent (25 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 567 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.
Other skills, from other repositories
verify-changes
Verify code changes by running the project's typecheck, build, lint, and targeted tests, then fix and re-run until clean. Use after editing any source file.
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).
iterative-refinement
Disciplined, measurable iteration for a substantial refinement or investigation: loop against verifiable pass/fail conditions, fan work out to subagents, and keep the main context lean. Use when improving something measurable over repeated cycles (tuning a metric or detector, refactoring against a regression bar)…
ap-policies
Attach a completion policy gate (shell check or judge-agent rubric) to a session or fan-in group so turn-end only passes when the gate is green, then optionally auto-commit pending human ack. Use when the user says "gate this session on tests passing", "attach a policy", "commit only if tests are green", "judge…
GitHub Issues
Triage GitHub issues, extract the real ask, and connect each issue to the relevant files, tests, or release surface before acting.
Test Driven Development
Drive behavior changes through a failing test, the smallest working implementation, and then cleanup once the behavior is locked.