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 agentmods add instructions/captkernel/skills_curator/claude-mdgit clone --depth 1 https://github.com/captkernel/Skills_CuratorWhat 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 | $0.01821 | $0.01821 |
| Opus 5 | $0.00911 | $0.00911 |
| Sonnet 5 | $0.00364 | $0.00364 |
| Haiku 4.5 | $0.00182 | $0.00182 |
Grade A, and why
Skills_Curator CLAUDE.md 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 2d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Curator — developer notes
This is the source repo for Skills Curator. The end-user README is README.md. This file is for maintainers and Claude Code instances working on the skill itself.
What this folder is
A plugin that handles judgment about other skills: pre-install evaluation, security scanning, project-aware recommendation, persistent decision history, cross-agent migration. Single-file Python engine + three SKILL.md variants + 3 slash commands + a plugin manifest.
The pitch: "Decide once. Re-decide never." Other tools manage skills; Skills Curator persists your judgment.
Three editions (as of v4.5.0)
The plugin ships three SKILL.md variants targeting two different runtimes:
| Edition | Runtime | Install path | Notes |
|---|---|---|---|
skills-curator-lite/ |
Claude Code (CLI) | Auto via npx skills add captkernel/Skills_Curator |
Default tier — no Python. Lite is tracked at its own internal version (2.0.0); only the plugin's outer version follows SemVer for the whole repo. |
skills-curator/ |
Claude Code (CLI) | --with-python opt-in via the same install command |
Python 3.10+ tier. VERSION constant in scripts/registry.py tracks plugin version. |
skills-curator-claudeai/ |
claude.ai (web + desktop) | Manual zip + upload via Settings → Capabilities → Skills | NOT in plugin.json skills[] — that array is for Claude Code's plugin loader. Shipping the claude.ai variant via that path would incorrectly drop it into ~/.claude/skills/. |
Why not all in plugin.json skills[]: The skills[] array tells Claude Code's plugin loader which subfolders to auto-install into ~/.claude/skills/. The claude.ai edition uses different persistence (Project Knowledge, not ~/.claude/), different invocation (natural language, not slash commands), and doesn't make sense as a Claude Code skill. It's distributed via the same repo but a different channel (the zip flow documented in its INSTALL.md).
Registry schema is shared across editions: v3.0 JSON. A registry written by any edition can be read by any other. Power users can roam a single registry across all three runtimes via Gist sync (Python edition has --sync; claude.ai edition has Mode C).
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.
- 2d ago First seen · 153 lines · 1,821 tokens per session scan A 4db341c924bf
Skills_Curator CLAUDE.md is an instructions file published in the GitHub repository captkernel/Skills_Curator (2 stars, last pushed 10d ago), licensed MIT. It adds 1,821 tokens to every session, about $0.0091 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 2026-08-31.
Other instructions, from other repositories
claude-skill-registry AGENTS.md
AGENTS.md instructions for majiayu000/claude-skill-registry, covering repository policy (core-first), repo identity map, edit routing, publish contract and case-conflict policy (core implementation).
claude-skill-registry CLAUDE.md
Claude Code instructions for majiayu000/claude-skill-registry, covering claude.md, repo map, how to decide where to edit, generated vs owned files in main and publish flow.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.