Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.
Borrowing it
Nothing to install: this file belongs to jeremylongshore/tons-of-skills-marketplace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jeremylongshore/tons-of-skills-marketplace/main/CLAUDE.mdgit clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplaceWrote 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/instructions/jeremylongshore/tons-of-skills-marketplace/claude-md)<a href="https://agentmods.dev/instructions/jeremylongshore/tons-of-skills-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/jeremylongshore/tons-of-skills-marketplace/claude-md/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/instructions/jeremylongshore/tons-of-skills-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/jeremylongshore/tons-of-skills-marketplace/claude-md.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 | $0.10899 | $0.10899 |
| Opus 5 | $0.05450 | $0.05450 |
| Sonnet 5 | $0.02180 | $0.02180 |
| Haiku 4.5 | $0.01090 | $0.01090 |
Grade A, and why
tons-of-skills-marketplace CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Defense-in-depth disallow list (3.7.0):** `disallowed-tools` — kebab-case string or YAML list of tool patterns. Removes those tools from the model while the skill is active. Parallel to (not a replacement for) `allow How it starts
The opening of the file, as written. The whole thing — 465 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.
Repository Overview
Tons of Skills — Claude Code plugins marketplace. Live at https://tonsofskills.com
Runtime: Node >=20.0.0, pnpm >=9.15.9. Node 18 causes silent workspace-resolution failures.
Package manager: pnpm everywhere except marketplace/ which uses npm (CI-enforced).
Contributor guidelines live in AGENTS.md — project structure, build/test/dev commands, style and naming, test conventions, commit/PR expectations, and the merge gates. Read it before starting work. (Session protocol lives in this file: the beads workflow in § Beads Issue Tracker — where bd prime is also the post-compaction context-recovery step — and the end-of-session push checklist in § Session Completion.)
Cross-session coordination — another Claude session may be in this repo
This repo is frequently worked in parallel with the intent-eval-platform umbrella session (that platform's CCPI validator + jrig-cli + kernel reach into this repo). Sessions are separate processes that share only the filesystem, so stay in sync via the shared surfaces:
- Read + append the shared journal on cross-repo work:
~/000-projects/CROSS-SESSION-LOG.md(append a dated line: what / branch or PR# / status). - Durable cross-cutting tasks: umbrella beads
~/000-projects/.beads/, labelcross-session(bd list --label cross-session). - Guard the working tree: this repo has ONE checkout; a concurrent session can
git checkout/resetit out from under you and wipe UNCOMMITTED work (happened 2026-07-01). Commit early, or do multi-step file work in agit worktree.
Full protocol (loaded by every session under /home/jeremy): /home/jeremy/CLAUDE.md § "Cross-session coordination".
Essential Commands
# Before ANY commit — regenerates marketplace.json, plugin package.jsons, README TOC
pnpm run sync-marketplace
# Quick sanity check (~30s)
./scripts/quick-test.sh
# Build & test
pnpm install && pnpm build
pnpm test && pnpm typecheck
pnpm lint
pnpm run verify # Full pipeline — what CI's `verify` job runs
# Validator (schema 4.1.0 — see 000-docs/SCHEMA_CHANGELOG.md)
python3 scripts/validate-skills-schema.py --verbose
python3 scripts/validate-skills-schema.py --marketplace --verbose
python3 scripts/validate-skills-schema.py --marketplace --populate-db freshie/inventory.sqlite
python3 scripts/validate-skills-schema.py --agents-only --verbose # agents only (kernel-strict gate)
# Unicode hygiene gate — Trapdoor / Trojan Source defense for SKILL.md /
# plugin.json / agent / command files. Default mode blocks on tag chars
# (U+E0000-E007F) + bidi overrides (CVE-2021-42574). --strict also blocks
# on zero-width / format chars outside the BOM position.
python3 scripts/validate-unicode-hygiene.py
python3 scripts/validate-unicode-hygiene.py --strict # tighter
python3 scripts/validate-unicode-hygiene.py path/to/file.md # one file
python3 -m unittest tests.test_validate_unicode_hygiene -v # regression suite
# Marketplace website
cd marketplace/ && npm run dev # localhost:4321
cd marketplace/ && npm run build
cd marketplace/ && npx playwright test
# Single test
cd packages/cli && pnpm test -- --grep "pattern"
# JRig behavioral eval — the published @intentsolutions/jrig-cli (bin `j-rig`),
# pinned as a root devDep. Invoke via `pnpm exec j-rig` so it resolves the
# repo's pinned version (node_modules/.bin/j-rig), NOT a global shim.
pnpm exec j-rig --version # → 0.1.2 (the real 7-layer CLI)
pnpm exec j-rig check <skill-dir> # Tier 3A: deterministic (~seconds, free, no API key, no DB)
# Real behavioral eval (opt-in, ~$2-5/skill) — needs the native better-sqlite3
# build (run `pnpm rebuild better-sqlite3` once; the build script is not
# auto-run on install). ALWAYS route through the wrapper — it runs j-rig
# against a /dev/shm scratch DB and records the verdict into forge_proofs via
# scripts/record-jrig-proofs.mjs. NEVER pass freshie/inventory.sqlite to
# `j-rig eval --db` directly: j-rig writes its own run tables into whatever
# --db it is given, which contaminates the tracked CMDB (and, pre-allowlist,
# leaked those tables to the public DoltHub record).
scripts/run-jrig-eval.sh --skill-dir <skill-dir> --plugin <catalog-name> \
--inventory-db freshie/inventory.sqlite
# DEEPSEEK_API_KEY is SOPS-decrypted in-process by the wrapper
# (intent-eval-lab/.env.sops; see the IEP umbrella CLAUDE.md credential
# table). Defaults: --provider deepseek --models deepseek-v4-flash — a real
# behavioral provider, this is ground truth; other providers (haiku/sonnet/
# opus via Anthropic, etc.) remain available via --provider/--models.
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 Changed · -2 lines · -11 tokens per session ed5c19500477
- 3d ago Changed · +2 lines · +108 tokens per session b8e762619163
- 9d ago Changed · +52 tokens per session df3240a94778
- 13d ago First seen · 465 lines · 10,750 tokens per session scan A 807730a146cf
tons-of-skills-marketplace CLAUDE.md is an instructions file published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 10,899 tokens to every session, about $0.0545 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).