agentmods.dev

toolshed CLAUDE.md

Project instructions for Toolshed, a marketplace that packages multiple Claude Code add-ons in one repository.

In plain words
What is it for?
They are for maintaining plugin files, marketplace metadata, versions, and the repository's validation workflow.
Why use it?
They explain how the repository is organized and how to validate it and keep its version information synchronized.

Instructions file

1 4mo ago A scan 2,347 tokens original MIT
View the source file knitli/toolshed
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 instructions/knitli/toolshed/claude-md
Clone the repo
git clone --depth 1 https://github.com/knitli/toolshed
Per session 2,347 This file is loaded in full into every session.
When invoked 2,347 The same file — it is already loaded in full.
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 $0.02347 $0.02347
Opus 5 $0.01174 $0.01174
Sonnet 5 $0.00469 $0.00469
Haiku 4.5 $0.00235 $0.00235

Measured 2d ago against content hash 0c68b0b4240a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

toolshed 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.

CLAUDE.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

Toolshed is a Claude Code plugin marketplace monorepo (knitli/toolshed). It packages multiple plugins for installation from a single source. Users add the marketplace with /plugin marketplace add knitli/toolshed and install individual plugins by name.

Commands

bun run validate          # Run marketplace validation (structure, JSON, version sync)

There is no build step, no test suite, and no linter beyond commitlint on PRs.

Architecture

All plugin logic is markdown prompts interpreted by Claude Code at runtime. There is no compiled code.

Version sync

Each plugin's package.json is the source of truth for that plugin's version — semantic-release bumps it on merge to main. The generate script reads the version from package.json and propagates it to plugin.json.

The marketplace version follows the same pattern at the repo root: package.json.version at repo root → marketplace.json.metadata.version, with semantic-release driven by .releaserc.json (generated). The release workflow runs bun scripts/generate.mts after each release to keep all mirrors in sync.

Release routing — scope is authoritative

Release routing is driven entirely by commit scope, not file paths. semantic-release-monorepo is not used. Each plugin's package.json.release uses @semantic-release/commit-analyzer releaseRules gated on its own scope, with a catchall { "release": false } that short-circuits the preset defaults. The marketplace release config at .releaserc.json does the same for scope marketplace. All release configs are fully generated by scripts/generate.mts; don't hand-edit.

Key files

  • .claude-plugin/marketplace.json — Discovery manifest listing all plugins with metadata. Top-level version field (metadata.version) is generated from root package.json.version by scripts/generate.mts.
  • plugins/<name>/.claude-plugin/plugin.json — Per-plugin manifest (name, version, description, mcpServers, userConfig). Generated.
  • plugins/<name>/package.json — npm package; version source of truth for that plugin. release field generated with a scope-gated config.
  • package.json (root) — version source of truth for the marketplace. The release field is NOT stored here; it lives in .releaserc.json (generated).
  • .releaserc.json — Marketplace-only semantic-release config; fully generated.
  • .commitlintrc.json — Enforces conventional commits. scope-enum = plugin names + marketplace; scope-empty: [2, 'never'] rejects unscoped commits.
  • .github/workflows/release.yml — Per-plugin semantic-release via matrix (max-parallel: 1), plus a release-marketplace job that needs: [release].
  • .github/workflows/validate.yml — PR gate: runs marketplace validation + commitlint

Read the full file on GitHub · 133 lines

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. 2d ago First seen · 133 lines · 2,347 tokens per session scan A 0c68b0b4240a

Subscribe to this mod's changes

toolshed CLAUDE.md is an instructions file published in the GitHub repository knitli/toolshed (1 stars, last pushed 4mo ago), licensed MIT. It adds 2,347 tokens to every session, about $0.0117 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.

claude-code-pluginclaude-skillscodex-plugincodex-skillsgemini-plugingemini-skills
Related

Other instructions, from other repositories

agent-skills AGENTS.md

AGENTS.md instructions for motherduckdb/agent-skills, covering motherduck skills -- agent guide, repo shape, non-negotiable content rules, product defaults to preserve and editing rules.

motherduckdb/agent-skills · 1,831 tokens

agent-skills CLAUDE.md

Claude Code instructions for motherduckdb/agent-skills, covering motherduck skills -- claude code context, what motherduck is, default routing, install notes and non-negotiable rules.

motherduckdb/agent-skills · 1,556 tokens

agent-skills GEMINI.md

Gemini CLI instructions for motherduckdb/agent-skills, covering motherduck skills for gemini cli, default routing, skill catalog, utility and workflow.

motherduckdb/agent-skills · 883 tokens

frappe-agent AGENTS.md

Instructions for Dkm0315/frappe-agent, covering frappe agent instructions, core behavior, bench guidance, app provenance and erpnext guidance.

Dkm0315/frappe-agent · 577 tokens

supergraph AGENTS.md

Instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).

datit309/supergraph · 1,664 tokens

frappe-agent copilot-instructions.md

Instructions for Dkm0315/frappe-agent: Treat this repository as Frappe, ERPNext, and Frappe ecosystem guidance for coding agents.

Dkm0315/frappe-agent · 286 tokens