agentmods.dev

registry-security

registry-security is a command for Claude Code from starslingdev/skills. It costs 23 tokens per session (364 once invoked), scanned A, original, MIT.

A maintainer-only check for a published coding skill’s security-audit status on skills.sh, a directory and audit service for skills.

In plain words
What is it for?
Run the audit for a skill, follow its verdict, report unresolved code findings, or monitor stale findings until the badge changes.
Why use it?
It helps distinguish a real security finding from an old badge or an unclear audit result, then identifies whether someone must act or the registry will update it later.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 maintainers/skills-registry-security/scripts/registry_audit.py <owner/repo/skill> --repo-root ..

not rated 80repo +30 yesterday A scan 23 tokens original MIT

Good fit Run the audit for a skill, follow its verdict, report unresolved code findings, or monitor stale findings until the badge changes.

Compare 6 commands from other repositories ↓
View source ↗ starslingdev/skills starsling.dev
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/starslingdev/skills
agentmods
npx agentmods add commands/starslingdev/skills/registry-security

Made for: Claude Code.

Wrote 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.

agentmods badge for registry-security

README.md
[![agentmods](https://agentmods.dev/badge/commands/starslingdev/skills/registry-security/github.svg)](https://agentmods.dev/commands/starslingdev/skills/registry-security)
Your own site
<a href="https://agentmods.dev/commands/starslingdev/skills/registry-security"><img src="https://agentmods.dev/badge/commands/starslingdev/skills/registry-security/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.

agentmods 80×15 button for registry-security

Your own site · 80×15
<a href="https://agentmods.dev/commands/starslingdev/skills/registry-security"><img src="https://agentmods.dev/badge/commands/starslingdev/skills/registry-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 364 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00364
Opus 5.5 $0.00009 $0.00146
Sonnet 5.5 $0.00005 $0.00073
Haiku 4.5 $0.00002 $0.00036

Measured 2mo ago against content hash 8041d7222e73, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

registry-security 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 2mo 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.

maintainers/skills-registry-security/commands/registry-security.md · 33 lines

What it actually says

Run the maintainer-only skills-registry-security skill against $ARGUMENTS (default starslingdev/skills/ci-secure if no target is given).

Read maintainers/skills-registry-security/SKILL.md and follow it. In short:

  1. Run the audit and read the NEXT ACTION verdict:

    python3 maintainers/skills-registry-security/scripts/registry_audit.py <owner/repo/skill> --repo-root .

    Add --no-install for the ~3s check instead of ~40s.

  2. Act on the verdict:

    • RESOLVED — the badge is clean. Report and stop.
    • ACTION_REQUIRED — a cited literal is still in HEAD. It is a real finding; surface it with the code and stop. Do not fix silently.
    • MONITOR — the finding is stale, there is nothing to patch, and the registry's own ~daily re-audit is what clears it. Arm the unattended watch per SKILL.md's "Drive it to green unattended" section and report only on a decision change.
    • DISAGREEMENT / UNVERIFIED — surfaces disagree or could not be classified. Re-check before trusting; never report a badge as clean.

Rails from SKILL.md that always apply: never rename or re-slug a published skill, never auto-file an issue on the registry's repo, and keep any research subagents read-only.

Changes

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.

  1. 2mo ago First seen · 33 lines · 23 tokens per session scan A 8041d7222e73

Subscribe to this mod's changes

registry-security is a command published in the GitHub repository starslingdev/skills (80 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 364 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.

CI and CDClaude CodeSecurityagent-skillsai-agentscontinuous-integrationdeveloper-tools
Related

registry-security compared with commands from other repositories

registry-security next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
registry-securitystarslingdev/skillsCommand80yesterdayMITA23Claude Code
dart-fix-cidartsim/dartCommand1.2kyesterdayBSD-2-ClauseA6Claude Code
domainsgotempsh/tempsCommand903yesterdayApache-2.0A0Claude Code
accessgotempsh/tempsCommand903yesterdayApache-2.0A0Claude Code
check-release-healthopenshift-eng/ai-helpersCommand122yesterdayApache-2.0A22Claude Code
merge-conflict-analysisrjmurillo/ai-agentsCommand49yesterdayMITA0GitHub Copilot
release-managerruvnet/agentic-flowCommand838yesterdaynoneA0Claude Code