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 warn-before-the-thing-you-are-warning-aboutgit 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/warn-before-the-thing-you-are-warning-about)<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/warn-before-the-thing-you-are-warning-about"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/warn-before-the-thing-you-are-warning-about/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/warn-before-the-thing-you-are-warning-about"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/warn-before-the-thing-you-are-warning-about.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 | $0.00041 | $0.00586 |
| Opus 5 | $0.00020 | $0.00293 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
warn-before-the-thing-you-are-warning-about 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
Something a user is about to do has a consequence they will not expect: an unsigned installer their OS will block, a command that rewrites history, a setting that removes a human from a loop, an export that leaves the sandbox.
It does not apply to consequences that are obvious from the label. "Delete" does not need a paragraph explaining that it deletes.
Do
- Put the caution above the control, in the reading order, not below it and not in a tooltip.
- Say what will happen in the user's terms — the exact dialog text they will see, the exact error — and then what to do about it.
- Reserve interruption for the irreversible. A confirmation on a narrowing action trains people to click through the confirmation that matters.
- If the surprise is unavoidable and benign, explain why it happens. "There is no code-signing certificate" converts an alarming dialog into an expected one.
Avoid
Warnings after the button, warnings in a collapsed section, and warnings that a user can dismiss before they have met the situation. All three are the same failure: the information arrives after the decision.
Avoid vagueness that sounds responsible. "Use with caution" tells the reader nothing they can act on, and its real function is to protect the author rather than the user.
Avoid warning about everything. A page where five things are flagged has flagged nothing, and the one genuinely dangerous item is now camouflaged.
Check
Read the page top to bottom as someone who has never seen it, and stop at the moment you would click. Was the caution above that point?
Then check the inverse: count the warnings on the surface. If there is more than one prominent one, decide which is the real one and demote the rest.
Risk
Front-loading cautions makes a page feel heavier and can scare off a user for whom the risk was never real. That cost is genuine and worth paying only where the surprise is genuine.
The failure mode of over-applying this is a product that reads as nervous about itself. If every screen opens with a disclaimer, the disclaimers become chrome and the reader skips them — which puts you back where you started, with worse copy.
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 · 65 lines · 41 tokens per session scan A 6406dae5aafa
warn-before-the-thing-you-are-warning-about is a skill published in the GitHub repository brcampidelli/chimera-agent (23 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 586 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
apply-mantel-styles
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.
web-artifacts-builder-v2
Suite of tools for creating elaborate, multi-component claude.ai HTML artefacts using modern frontend web technologies (React 19, Tailwind CSS v4, shadcn/ui). Use for complex artefacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artefacts.
diagrams-as-code
Use only when creating architecture diagrams with Python's diagrams library (mingrammer/diagrams).
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, UI mockups, product shots, or transparent-background cutouts. Use when the result should be an image asset rather than repo-native SVG, HTML/CSS, or canvas.
mermaid-diagrams
Use the mermaid-diagrams skill whenever you are creating or updating mermaid diagrams. Provides guidance on mermaid best practices.
html-design-examples
Reference gallery of polished single-file HTML artifacts demonstrating effective ways to communicate ideas through HTML. Use when the user wants to explain, showcase, demo, plan, review, or present an idea within an HTML file.