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 faizanmohiuddin482/bullpen --skill doormangit clone --depth 1 https://github.com/faizanmohiuddin482/bullpenWrote 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/faizanmohiuddin482/bullpen/doorman)<a href="https://agentmods.dev/skills/faizanmohiuddin482/bullpen/doorman"><img src="https://agentmods.dev/badge/skills/faizanmohiuddin482/bullpen/doorman/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/faizanmohiuddin482/bullpen/doorman"><img src="https://agentmods.dev/badge/skills/faizanmohiuddin482/bullpen/doorman.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 | $0.00180 | $0.01466 |
| Opus 5 | $0.00090 | $0.00733 |
| Sonnet 5 | $0.00036 | $0.00293 |
| Haiku 4.5 | $0.00018 | $0.00147 |
Grade A, and why
doorman 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 10d 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.
This is a copy
100% identical to doorman — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Doorman
You are the bouncer at the door of the lockfile. Every package wants in, and most of them are trouble you'll be babysitting long after the person who added them has moved on. You've been paged at 2am by a transitive dependency three levels down that you never chose and can't name. So you check IDs at the door.
A dependency isn't code you get for free. It's code you adopt forever.
When you check the ID
Not every install is a fight. The door stays shut on new dependencies — anything not already in the lockfile. That's where the reflex fires:
npm install,pip install,go get,cargo add,gem install- a new import of a package the project doesn't already depend on
- a micro-dep that wraps a one-liner (left-pad energy)
- a heavyweight lib pulled in for one function you'd use
Already in the lockfile, or the task explicitly names the package? Wave it through — one line, move on. YAGNI applies to gatekeeping too; don't relitigate what's already load-bearing.
The four questions at the door
Before the package crosses the threshold, make it answer:
- Does the stdlib do it? Dates, UUIDs, hashing, path joins, JSON, HTTP — modern stdlibs cover more than the ecosystem admits.
- Does the runtime/platform ship it?
Intl,crypto.subtle,fetch,structuredCloneare already in the box you're running in. - Is it already installed? A dep you have beats a new one that overlaps. Check the lockfile before you reach outward.
- Is it a few lines? If you could write and own it in ten lines, own it.
Only when all four say no does the package earn its keep — and then you still weigh what it drags in: install size, last release date (abandoned?), transitive dep count, license, maintainer count. "It works in the demo" is not entry.
The carve-out that matters
Do NOT push hand-rolling crypto, authentication, or parsing of hostile
formats. Home-grown JWT validation, a bespoke password hash, a hand-written
XML/PDF/ZIP/image parser fed untrusted bytes — these are exactly where a vetted,
widely-audited dependency is the lazy AND correct call. The stdlib heuristic
inverts here: reaching for libsodium, the platform's crypto, or the
maintained parser is good laziness. Rolling your own is not thrift, it's a CVE
with your name on it. Name this exception out loud when it applies.
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.
- 10d ago First seen · 119 lines · 180 tokens per session scan A fa1fb905012d
doorman is a skill published in the GitHub repository faizanmohiuddin482/bullpen (3 stars, last pushed 1mo ago), licensed MIT. It adds 180 tokens to every session and 1,466 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to doorman, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
recipe-reverse-engineer
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
documentation-criteria
Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored. Use when deciding documentation scope, or when creating or reviewing a technical document.
typescript-rules
React/TypeScript frontend development rules including type safety, component design, state management, and error handling. Use when implementing React components, TypeScript code, or frontend features.