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 chimera-state-what-you-did-not-checkgit 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/chimera-state-what-you-did-not-check)<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/chimera-state-what-you-did-not-check"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/chimera-state-what-you-did-not-check/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/chimera-state-what-you-did-not-check"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/chimera-state-what-you-did-not-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 64 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00042 | $0.00888 |
| Opus 5 | $0.00021 | $0.00444 |
| Sonnet 5 | $0.00008 | $0.00178 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
chimera-state-what-you-did-not-check 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
You are delivering something that reads as a survey: a code review, a security pass, "the three biggest problems", a prioritised backlog, a comparison of options. Anything where you looked at some of a space and produced an ordering.
It does not apply to answering a bounded question — "does this function handle an empty list?" — where the scope is already the whole of what was asked. The risk here is specific to output whose form is a list of the worst things, because that form carries an implied "of everything" the reader will supply for free.
Do
- Open with the scope, before the findings. Name what you actually read: paths or globs, the
commit or branch, and whether you ran anything or only read.
Reviewed: src/api/*.py at 4f2a1c9, static read only, no tests executed. - List the exclusions with their reason, and keep the reasons concrete: no access to the migrations, the integration suite needs credentials I do not have, the frontend was out of budget for this pass.
- Scope every superlative to what you read. Not "the worst issue is the missing auth check" but "the worst of the six handlers I read". The two sentences cost the same and mean different things.
- Separate "checked and clean" from "not checked". A reader treats silence as a clean bill; only one of those two states earns it.
- Name the unchecked thing most likely to outrank your current number one, so the reader knows what the next pass should buy. If nothing plausible could, say that too — it is a real finding.
Avoid
Reporting "no SQL injection found" after a pass that never opened the database layer. The
sentence is literally true and functions as a clearance. Write "did not review db/ — no access
to the migration files" and the same pass now says what it knows.
Avoid putting the scope in a closing paragraph under a heading like Limitations. Readers act on the top of the document; a caveat below the ranking arrives after the decision it was supposed to qualify.
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 · 83 lines · 42 tokens per session scan A 360a547ed02e
chimera-state-what-you-did-not-check is a skill published in the GitHub repository brcampidelli/chimera-agent (25 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 888 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
code-review
Performs structured code review on a file or directory.
code-review-recent-changes
Review recent changes since a fixed point (commit, branch, tag, or merge-base) across three independent axes - Standards, Spec, and Maintainability - producing severity-ordered findings with an explicit verdict. Use when the user wants to review a branch, a PR, or recent committed changes.
code-review
Use this skill after completing multiple, complex software development tasks before informing the user that work is complete.
code-simplification
Use this skill when you need to review and refactor code to make it simpler, more maintainable, and easier to understand. Helps with identifying overly complex solutions, unnecessary abstractions.
self-review
Use to critically self-review your changes, or when you want to delegate the review to a sub-agent.
autoreview
Run a structured code review (Codex default, Claude optional) as a closeout check on a local or PR branch before commit or ship.