registry-pick

registry-pick is a command for Claude Code from lglucas/ai-dev-operating-system. It costs 42 tokens per session (487 once invoked), scanned A, original, MIT.

A recommendation command that suggests external project packs from a registry based on the project's design, technology stack, business area and compliance needs.

In plain words
What is it for?
Use it during project planning to get prioritized must-install, recommended, optional and skipped pack suggestions.
Why use it?
It helps choose relevant reusable packs without installing unsuitable ones. The command only recommends packs and leaves installation for later.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Part of the ai-dev-operating-system plugin — 28 skills, 11 commands, 12 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add commands/lglucas/ai-dev-operating-system/registry-pick
Clone the repo
git clone --depth 1 https://github.com/lglucas/ai-dev-operating-system

Made for: Claude Code.

Or install ai-dev-operating-system, the plugin that ships this one along with the rest of its 28 skills, 11 commands, 12 agents, 1 hook.

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-pick

README.md
[![agentmods](https://agentmods.dev/badge/commands/lglucas/ai-dev-operating-system/registry-pick.svg)](https://agentmods.dev/commands/lglucas/ai-dev-operating-system/registry-pick)
Your own site
<a href="https://agentmods.dev/commands/lglucas/ai-dev-operating-system/registry-pick"><img src="https://agentmods.dev/badge/commands/lglucas/ai-dev-operating-system/registry-pick.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 487 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.00487
Opus 5 $0.00021 $0.00244
Sonnet 5 $0.00008 $0.00097
Haiku 4.5 $0.00004 $0.00049

Measured 6d ago against content hash 7b2a2fe55caa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

registry-pick 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 6d 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.

.claude/commands/registry-pick.md · 49 lines

What it actually says

/registry-pick

Recommend external repository packs from the registry that fit the current project.

Expected input

/registry-pick

Optional arguments:

/registry-pick stack="<stack>" domain="<domain>" compliance="<compliance>"

If arguments are omitted, the skill reads project signals from whatever exists at that point in the wizard — the input contract differs per pass:

Pass NÃO lê
3.1 design docs/business/BUSINESS-PLAN.md v0.0.2, knowledge-base/ Product Brief e Technical Plan — ainda não existem
4.3 stack tudo acima + docs/product/PRODUCT-BRIEF.md, docs/technical/TECHNICAL-PLAN.md, prototype-lab/, manifestos (package.json, Anchor.toml…)

Pedir na passada de design um arquivo que a Fase 3 ainda não produziu trava o wizard sem motivo.

Actions

  1. Invoke the registry-pick skill.
  2. Read docs/registry/INDEX.md and the relevant packs/<slug>.md one-pagers.
  3. Match project signals against pack tags and fit-signals.
  4. Output a prioritized recommendation: must-install / recommended / optional / skipped.
  5. Stop before installing — surface install commands but defer execution to the user.

When to use

  • At WIZARD.md stage 3.1 — design-scoped pass, before the Prototype Lab. Output: docs/technical/registry-pick-design.md.
  • At WIZARD.md stage 4.3 — full stack pass, after the Technical Plan. Output: docs/technical/registry-pick.md.
  • When a new domain need surfaces mid-build.
  • After a new pack is added to docs/registry/.

Cross-references

  • Skill: .claude/skills/registry-pick/SKILL.md
  • Registry: docs/registry/INDEX.md
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. 6d ago First seen · 49 lines · 42 tokens per session scan A 7b2a2fe55caa

Subscribe to this mod's changes

registry-pick is a command published in the GitHub repository lglucas/ai-dev-operating-system (11 stars, last pushed 27d ago), licensed MIT. It adds 42 tokens to every session and 487 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.