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.
git clone --depth 1 https://github.com/luongnv89/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/agents/luongnv89/skills/registry-checker)<a href="https://agentmods.dev/agents/luongnv89/skills/registry-checker"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/registry-checker/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/agents/luongnv89/skills/registry-checker"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/registry-checker.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 | $0.00021 | $0.01050 |
| Opus 5 | $0.00010 | $0.00525 |
| Sonnet 5 | $0.00004 | $0.00210 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
registry-checker 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 9d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Registry Checker Agent
Check package registry availability across npm, PyPI, Homebrew, and apt, returning status and owner information.
Input
{
"name": "myproductname"
}
Process
Check each registry independently via WebFetch:
1. npm Registry
- URL:
https://registry.npmjs.org/[NAME] - Taken if: Returns JSON with package data (not 404)
- Extract: Package name, owner, description, last publish date
- Return:
availableif 404takenif valid package found- Owner and metadata if taken
2. PyPI
- URL:
https://pypi.org/pypi/[NAME]/json - Taken if: Returns JSON with package data (not 404)
- Extract: Package name, author, description, last release date
- Return:
availableif 404takenif valid package found- Author and metadata if taken
3. Homebrew
- URL:
https://formulae.brew.sh/api/formula/[NAME].json - Taken if: Returns JSON (not 404)
- Extract: Formula name, description, repository
- Return:
availableif 404takenif valid formula found- Repo and metadata if taken
4. apt (Debian/Ubuntu)
- Search query:
"[NAME]" site:packages.debian.org OR site:packages.ubuntu.com - Taken if: Package listing found
- Extract: Package name, version, maintainer
- Return:
availableif no package foundtakenif package exists- Maintainer and version if taken
Output
Return JSON with this structure:
{
"name": "myproductname",
"timestamp": "2026-03-24T10:30:00Z",
"registry_status": {
"npm": {
"status": "available|taken|error",
"registry_url": "https://www.npmjs.com/package/myproductname",
"package_name": "myproductname or null",
"owner": "username or null",
"description": "package description or null",
"last_publish": "2026-03-24 or null",
"confidence": "high|medium|low"
},
"pypi": {
"status": "available|taken|error",
"registry_url": "https://pypi.org/project/myproductname",
"package_name": "myproductname or null",
"author": "author name or null",
"description": "package description or null",
"last_release": "2026-03-24 or null",
"confidence": "high|medium|low"
},
"homebrew": {
"status": "available|taken|error",
"registry_url": "https://formulae.brew.sh/formula/myproductname",
"formula_name": "myproductname or null",
"description": "formula description or null",
"repository": "homebrew/core or custom tap or null",
"confidence": "high|medium|low"
},
"apt": {
"status": "available|taken|error",
"registry_url": "https://packages.debian.org/search?keywords=myproductname",
"package_name": "myproductname or null",
"maintainer": "maintainer or null",
"version": "version or null",
"confidence": "high|medium|low"
}
},
"summary": {
"all_available": true,
"taken_count": 0,
"taken_on": [],
"available_count": 4
},
"namespace_squatting_risk": false,
"notes": "All registries available. Safe to claim across all platforms."
}
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.
- 9d ago First seen · 134 lines · 21 tokens per session scan A a7a474553e0c
registry-checker is an agent published in the GitHub repository luongnv89/skills (123 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,050 once invoked, about $0.0001 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 agents, from other repositories
2-generate-tasks
Convert PRDs into development task lists.
cf-reviewer-security
Security review specialist. Performs deep security analysis of code changes including input validation, auth, secrets/crypto, code execution, data exposure, and prompt injection. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Includes exploit scenarios for Critical findings. Traces data…
cf-reviewer-rules
Project rules compliance specialist. Checks code changes against AGENTS.md project rules. Only flags violations of rules with MUST/SHOULD/ALWAYS/NEVER language. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Skipped in QUICK review mode.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
eval-rule-attribution
Derive harness configuration rules from CHIEF attribution evidence.
vision
Analyze images with task-aware visual reasoning.