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 build-the-gate-before-the-contentgit 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/build-the-gate-before-the-content)<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/build-the-gate-before-the-content"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/build-the-gate-before-the-content/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/build-the-gate-before-the-content"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/build-the-gate-before-the-content.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 | $0.00598 |
| Opus 5 | $0.00017 | $0.00299 |
| Sonnet 5 | $0.00007 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
build-the-gate-before-the-content 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
You are about to build something that will need a rule enforced across it — a style constraint, a freshness check, a schema, a link validator, a budget. The natural order is to build the thing and add the check once there is something to check.
It does not apply to a check you are adding to code that already exists; that is a different and harder job, and the answer there is a ratchet, not a wall.
Do
- Add the check in the first commit, before there is any content for it to fail on. It passes trivially, which is the point: it starts life green.
- Give it a failure message that says what to run. A gate whose output is
assert Falsegets deleted by the next person who hits it at 2am. - Write the check so it fails on the first violation, not the hundredth. Ratchets are for legacy; greenfield starts at zero.
- When the check does fire, fix the content. Every time you change the check instead, note in the commit message which case forced it.
Avoid
"We will turn this on once the pages are written." By then the check has a backlog, turning it on
means a day of unrelated fixes, and the cheapest path is a skip list that never shrinks.
Avoid also loosening a gate in the same commit as the feature that tripped it. The loosening is invisible in a large diff, and it is the exact moment a gate stops being one — so it belongs in its own commit with its own explanation.
Check
Introduce a violation on purpose and confirm the build goes red — then remove it. Do this on the day you write the gate, not later.
A gate nobody has watched fail is not a gate; it is a file that claims to be one.
Risk
A gate written before the content encodes an assumption about content that does not exist yet, and some of those assumptions turn out wrong. Expect to narrow it once or twice early on.
That narrowing is the dangerous moment. Each one makes the rule weaker, and a rule narrowed three times without anybody noticing is a rule that no longer covers the case it was written for. Pin every narrowing with the failing example that caused it.
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 · 62 lines · 35 tokens per session scan A 58c3de3bf732
build-the-gate-before-the-content 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 598 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
verify-changes
Verify code changes by running the project's typecheck, build, lint, and targeted tests, then fix and re-run until clean. Use after editing any source file.
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).
iterative-refinement
Disciplined, measurable iteration for a substantial refinement or investigation: loop against verifiable pass/fail conditions, fan work out to subagents, and keep the main context lean. Use when improving something measurable over repeated cycles (tuning a metric or detector, refactoring against a regression bar)…
ap-policies
Attach a completion policy gate (shell check or judge-agent rubric) to a session or fan-in group so turn-end only passes when the gate is green, then optionally auto-commit pending human ack. Use when the user says "gate this session on tests passing", "attach a policy", "commit only if tests are green", "judge…
GitHub Issues
Triage GitHub issues, extract the real ask, and connect each issue to the relevant files, tests, or release surface before acting.
Test Driven Development
Drive behavior changes through a failing test, the smallest working implementation, and then cleanup once the behavior is locked.