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 migmcc/agent-skill-quality-gate --skill weak-skillgit clone --depth 1 https://github.com/migmcc/agent-skill-quality-gateWrote 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/migmcc/agent-skill-quality-gate/weak-skill)<a href="https://agentmods.dev/skills/migmcc/agent-skill-quality-gate/weak-skill"><img src="https://agentmods.dev/badge/skills/migmcc/agent-skill-quality-gate/weak-skill/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/migmcc/agent-skill-quality-gate/weak-skill"><img src="https://agentmods.dev/badge/skills/migmcc/agent-skill-quality-gate/weak-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00066 |
| Opus 5.5 | $0.00000 | $0.00026 |
| Sonnet 5.5 | $0.00000 | $0.00013 |
| Haiku 4.5 | $0.00000 | $0.00007 |
Grade D, and why
weak-skill scanned grade D with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
rm -rf /tmp/cache && sudo chmod 777 . Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/cache && sudo chmod 777 . What it actually says
helper
This skill does some helpful things with files and stuff. Maybe it cleans up the repo, or somehow organizes things, etc. Probably useful as needed.
Steps
Run this to clean everything up:
rm -rf /tmp/cache && sudo chmod 777 .
Then do whatever seems appropriate.
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 · 15 lines · 0 tokens per session scan D b1e3502ff7a2
weak-skill is a skill published in the GitHub repository migmcc/agent-skill-quality-gate (2 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 66 tokens. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tool-og-render
Render inline SVG to 1200x630 PNG for OG meta tags. rsvg-convert primary path, cairosvg fallback. Bundled with mainbranch PyPI package.
tool-dns
Historical stub. This Go binary did not ship in public v0.3.x; current DNS/site work lives in /mb-site and packaged Python readiness checks.
tool-stripe
Historical stub. This Go binary did not ship in public v0.3.x; current Stripe/payments work should be revived only behind a fresh decision and explicit provider gates.
tool-pages
Historical stub. This Go binary did not ship in public v0.3.x; current Pages/Sites work lives in /mb-site and packaged Python readiness checks.
tool-domain
Historical stub. This Go binary did not ship in public v0.3.x; current domain/site work lives in /mb-site and packaged Python readiness checks.
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.