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-run-the-projects-own-gate-commandgit 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-run-the-projects-own-gate-command)<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/chimera-run-the-projects-own-gate-command"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/chimera-run-the-projects-own-gate-command/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-run-the-projects-own-gate-command"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/chimera-run-the-projects-own-gate-command.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 | $0.00037 | $0.01155 |
| Opus 5 | $0.00018 | $0.00577 |
| Sonnet 5 | $0.00007 | $0.00231 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
chimera-run-the-projects-own-gate-command 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
You are about to run the project's quality gate — lint, type check, tests — and report the result as
evidence that a change is safe. The temptation is to narrow it ("I only touched chimera/") or to
tighten it ("--strict is surely better").
It does not apply to exploration. Running pytest tests/test_governed_surfaces.py -x while
iterating on one file is the right thing to do; the rule is about what you may then call the gate.
A narrowed run is a debugging aid, never the verification.
Do
- Find where the command is written down, and name ONE source as canonical. In Chimera that is the
checktarget in theMakefile—make check— because a target is executable and a prose line is a copy of one. The three checks it runs areruff check .,mypy chimeraandpytest -q. - Run the canonical form byte-for-byte. No added path argument, no added flag, no substituted
runner. Beware that a prose copy may differ in ways that look cosmetic and are not:
Makefile:21wraps it asuv run --no-sync,CONTRIBUTING.md:105asuv run --extra dev --extra desktop. Same tool, different environments — which is exactly why one of them has to be the source. - If two sources disagree, treat the CI workflow as authoritative, run that, and fix the stale doc in
the same PR —
CONTRIBUTING.mdcarried a wrongmypy --strictline for a while, and a stale instruction propagates to everyone who reads it. - If the canonical command cannot run in your environment, say the gate did not run. On Windows the
local
.venvis broken (litellm wants Rust/MSVC), so the gate runs in WSL — moving the shell is allowed, editing the command is not. - Report the command and its output verbatim, not a summary of how it went.
Avoid
Two near-misses, both real, both in one session, and note they fail in opposite directions:
mypy --strict chimera # WRONG — lies toward failure
mypy chimera # right
The explicit flag overrides the project's own warn_unused_ignores = false in pyproject.toml and
reports roughly fifteen unused-ignore errors in files nobody touched. That nearly became a bug
report filed against clean code.
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 · 95 lines · 37 tokens per session scan A 12e60e2bbe0f
chimera-run-the-projects-own-gate-command is a skill published in the GitHub repository brcampidelli/chimera-agent (25 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 1,155 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
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
synthesize-report
Produces a citation-grounded summary across one or more workspace source files for summaries, briefings, literature reviews, or comparisons.
data-analysis
Statistical data analysis skill — use when the user asks to analyze numbers, compute statistics, or summarize datasets.
summarizer
Use when the user asks for a summary, TL;DR, or condensed version of any content.
weknora-shared
Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.
skill-creator-primer
You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).