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-ground-it-in-the-sourcegit 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-ground-it-in-the-source)<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/chimera-ground-it-in-the-source"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/chimera-ground-it-in-the-source/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-ground-it-in-the-source"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/chimera-ground-it-in-the-source.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 | $0.00035 | $0.01078 |
| Opus 5 | $0.00017 | $0.00539 |
| Sonnet 5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
chimera-ground-it-in-the-source 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 11d 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 write a call into someone else's library, framework or CLI: a method name, a keyword argument, a config key, the shape of a return value, a flag. This applies most sharply when recall feels confident, because confidence is produced the same way whether or not the API exists.
It does not apply to the language's own builtins you exercise constantly, and it is not an
instruction to fetch documentation before writing dict.get. The line is whether being wrong would
be caught immediately by the next thing you run.
Do
- Get the version that is actually installed, not the one you remember reading about:
uv pip show <pkg>, orpython -c "import pkg; print(pkg.__version__)". - Read the installed thing.
python -c "import inspect, pkg; print(inspect.signature(pkg.fn))", or open the file undersite-packages, or run--helpon the binary that is on PATH. This is the authority, because it is the code that will execute. - When you use a blog post, a README on the web, or your own recall, treat it as a hypothesis and confirm it against step 2. Docs sites describe the latest release; your lockfile may not pin it.
- Exercise the call once in a throwaway snippet and print the actual return value before writing
code that indexes into your assumption of it. Nested shapes —
["choices"][0]["message"]— are where memory is least reliable and least likely to fail loudly. - Leave the evidence next to the code: the version, and the signature or help output you read. A comment or the PR body is enough, and it tells the next reader what the code was written against.
Avoid
Writing API-shaped text. The failure is not a typo — a typo raises immediately and gets fixed in seconds. It is a name that obeys every one of the library's naming conventions and does not exist:
A real one from this repository, and the shape is the point — the guess was not absurd, it was reasonable:
# Plausible: snapshots live in checkpoint.py, so the diff of two snapshots should too.
from chimera.core.checkpoint import WorkspaceGuard, diff_snapshots # ImportError
# Where it actually is. One grep, before writing the line, would have found it.
from chimera.core.checkpoint import WorkspaceGuard
from chimera.evolution.diff_gate import diff_snapshots
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.
- 11d ago First seen · 95 lines · 35 tokens per session scan A 9a51bb6b117c
chimera-ground-it-in-the-source is a skill published in the GitHub repository brcampidelli/chimera-agent (23 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 1,078 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-search
Search a codebase efficiently with ripgrep regular expressions, file globs, and git history search. Use to locate symbols, usages, and definitions instead of reading whole files.
code-review
Performs structured code review on a file or directory.
systematic-debugging
Applies a modified Fagan Inspection methodology to resolve persistent bugs and complex issues. Use when several fix or debugging attempts have already failed and a methodical root-cause analysis warranting a Fagan inspection is needed. For first-pass diagnosis of a reproducible bug or regression use…
reframe-voice
Write, rewrite, or review content in the evidence-led reframe voice style. Use when the user explicitly asks to write in "reframe voice" or "reframe style". Do NOT use for general writing tasks.
goal-flight-doctor
Use when the user invokes /goal-flight doctor or asks for Goal Flight readiness diagnostics on the current repository.
Docker Management
Manage Docker containers, images, volumes, networks, and Compose stacks — lifecycle ops, debugging, cleanup, and Dockerfile optimization.