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 keep-the-caveat-with-the-numbergit 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/keep-the-caveat-with-the-number)<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/keep-the-caveat-with-the-number"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/keep-the-caveat-with-the-number/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/keep-the-caveat-with-the-number"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/keep-the-caveat-with-the-number.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 | $0.00028 | $0.00636 |
| Opus 5.5 | $0.00011 | $0.00254 |
| Sonnet 5.5 | $0.00006 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
keep-the-caveat-with-the-number 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
You are putting a measured figure somewhere a reader will see it: a README, a landing page, release notes, a dashboard, a report. The figure is true and it needs a sentence beside it to not mislead — the sample was small, the slice was easy, the effect was not significant, the benchmark was ours.
It does not apply to a figure whose meaning is complete on its own. "Build took 41 seconds" needs nothing.
Do
- Write the caveat first, before the number. If you cannot state the limitation in one sentence, you do not yet understand the measurement well enough to publish it.
- Make the caveat structurally attached. Put it in the same component, the same table row, the same function return — something that cannot render the figure without it.
- Put it above the number, or beside it. Not below.
- Make the number itself derived: read it from the artifact the measurement produced, so it moves when the measurement moves.
Avoid
The number in the headline and the caveat in a footnote, an asterisk, a collapsed section, or the paragraph after. Those are all the same bug with different styling: the reader forms the belief first, and a correction arriving afterwards has to overcome a belief that already exists.
Avoid also the second-order version — a component that can render the figure with the caveat omitted. If the qualification is an optional argument, it will be omitted, and it will be omitted by someone tightening a paragraph who never intended to change the meaning.
And do not paraphrase a caveat that was written carefully. Rewording is where "not significant on its own" becomes "close to significant".
Check
Try to write the number without the caveat and watch it fail. Delete the qualification argument, or put a bare figure in a page, and run the build.
If it compiles, the pairing is a convention rather than a mechanism, and conventions survive exactly as long as nobody is in a hurry.
Risk
Over-applied this makes ordinary reporting heavy: not every number is a benchmark, and a caveat on a figure that does not need one trains people to skip caveats.
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.
- 1mo ago First seen · 66 lines · 28 tokens per session scan A 98a524b60de3
keep-the-caveat-with-the-number is a skill published in the GitHub repository brcampidelli/chimera-agent (29 stars, last pushed today), licensed Apache-2.0. It adds 28 tokens to every session and 636 once invoked, about $0.0001 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 2026-08-30.
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.
summarizer
Use when the user asks for a summary, TL;DR, or condensed version of any content.
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).
home-assistant
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.
authoring-claude-md
Creating and maintaining CLAUDE.md project memory files and .claude/rules/ rule files that provide non-obvious codebase context. Use when (1) creating a new CLAUDE.md for a project, (2) adding architectural patterns or design decisions to existing CLAUDE.md, (3) capturing project-specific conventions that aren't…