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 terrylica/cc-skills --skill c-meta-governancegit clone --depth 1 https://github.com/terrylica/cc-skillsWrote 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/terrylica/cc-skills/c-meta-governance)<a href="https://agentmods.dev/skills/terrylica/cc-skills/c-meta-governance"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/c-meta-governance/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/terrylica/cc-skills/c-meta-governance"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/c-meta-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.01803 |
| Opus 5 | $0.00017 | $0.00901 |
| Sonnet 5 | $0.00007 | $0.00361 |
| Haiku 4.5 | $0.00003 | $0.00180 |
Grade A, and why
crucible-meta-governance 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-governance — 6 decision-layer patterns
Self-Evolving Skill: If any pattern here misled decisions, update the section AND append to
references/evolution-log.md. Don't defer.
These patterns are meta-level — they're about the investigation itself, not its content. Invoke when a decision must be made: pivot vs persist, kill vs narrow, ship vs hold.
1. Physical-constraint-first pivot
When brute force yields null, extract the execution constraint and redesign the hypothesis class to fit it. Don't iterate on a hypothesis that ignores reality.
Session example: 17 directional-signal null campaigns → user pivoted:
"What's the best strategy for a highly random walk market?" "I can only trade on a traditional MT5 broker that allows hedging positions."
From this came the synthetic straddle (BUY_STOP + SELL_STOP pending orders, OCO). Constraint-driven design unlocked the strategy class. The math (diffusive displacement in random walks: E[|ΔS|] > 0) was always available; what was missing was honoring the execution venue.
Ask yourself:
- What execution venue is the user actually on?
- What types of orders are possible?
- What's the realistic slippage / commission / spread?
- What position-sizing constraints apply?
If the hypothesis doesn't survive these questions, pivot the hypothesis, not the statistics.
2. Incremental artifact promotion (/tmp → repo early)
Move findings from /tmp/ to the persistent repo (audits/YYYY-MM-DD-slug/) as soon as a result survives two independent tests, not "when done".
Session anti-pattern: reproducers written in /tmp/ during exploration, causing reproducibility loss on reboot. The moment a result passed Gate C (OOS) it should have been promoted — not after the 4-gate suite completed.
Promotion triggers (at least one required):
- Result passed shuffled-null z > 3 AND hasn't been contradicted
- An agent synthesized a verdict that supersedes an earlier one
- A reproducer script ran successfully twice
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 169 lines · 35 tokens per session scan A 51aee0df9a16
crucible-meta-governance is a skill published in the GitHub repository terrylica/cc-skills (73 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,803 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
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
email-systems
Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.
customer-persona-builder
Data-driven customer persona development combining market research, user behavior analysis, and segmentation frameworks. Use when creating buyer personas, ideal customer profiles (ICPs), or user archetypes.
devops-cloud
DevOps, cloud infrastructure, and platform engineering. Use when working with AWS, GCP, Azure, Kubernetes, Terraform, CI/CD pipelines, or infrastructure as code.
generic-design-system
Complete design system reference for any project - colors, typography, spacing, components, animations. Adapts to project theme and tech stack. Use when implementing UI, choosing colors, creating animations, or ensuring brand consistency. For new design systems, use ui-research skill first.
generic-code-reviewer
Review code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Supports any tech stack - HTML/CSS/JS, React, TypeScript, Node.js, Python, NestJS, Next.js, and more. Use when completing features, before commits, or reviewing pull requests.