claude-plugins AGENTS.md

A set of working instructions for the jontsai/claude-plugins codebase, a marketplace that contains Claude Code plugins and validation scripts.

In plain words
What is it for?
Use it when editing plugins, skills, hooks, marketplace metadata, or validation-related files in that repository.
Why use it?
It helps coding agents follow the repository’s required file structure, configuration formats, and checks before changes are committed.

Instructions file for CodexOpenCode

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/jontsai/claude-plugins/agents-md
Clone the repo
git clone --depth 1 https://github.com/jontsai/claude-plugins

Made for: Codex, OpenCode.

Per session 539 This file is loaded in full into every session.
When invoked 539 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 $0.00539 $0.00539
Opus 5 $0.00269 $0.00269
Sonnet 5 $0.00108 $0.00108
Haiku 4.5 $0.00054 $0.00054

Measured 3d ago against content hash e64c8b992fe4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-plugins AGENTS.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 3d 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.

AGENTS.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidelines

Guidelines for LLMs working on this codebase.

Project Overview

This is a Claude Code plugins marketplace. It contains:

  • Marketplace definition: .claude-plugin/marketplace.json
  • Plugins: plugins/<name>/ directories
  • Validation scripts: scripts/validate_*.py
  • CI workflow: .github/workflows/validate.yml

Key Constraints

Plugin Structure

  1. Each plugin needs .claude-plugin/plugin.json with:

    • name, description, version, author
  2. Skills are auto-discovered from skills/*/SKILL.md

    • Do NOT add explicit skills array to marketplace.json
    • Each SKILL.md needs frontmatter with name and description
  3. hooks.json format is specific:

    • Must be object keyed by event name, NOT an array
    • Use ${CLAUDE_PLUGIN_ROOT} for paths in commands

Validation

Always run before committing:

./scripts/validate.sh

Or run individual validators:

python3 scripts/validate_json.py
python3 scripts/validate_marketplace.py
python3 scripts/validate_skills.py
python3 scripts/validate_hooks.py

Common Mistakes to Avoid

  1. hooks.json as array: Must be {"hooks": {"EventName": [...]}} not {"hooks": [...]}
  2. Explicit skills array: Don't add - causes path doubling
  3. Missing plugin.json: Each plugin needs .claude-plugin/plugin.json
  4. echo for colors: Use printf with \e[0;32m escapes in Makefiles

Testing Plugin Installation

# Add marketplace
/plugin marketplace add jontsai/claude-plugins

# Install plugin
/plugin install researcher@jontsai

# Check installation
/plugin list

File Locations

Purpose Path
Marketplace def .claude-plugin/marketplace.json
Plugin metadata plugins/<name>/.claude-plugin/plugin.json
Plugin hooks plugins/<name>/hooks/hooks.json
Skills plugins/<name>/skills/<skill>/SKILL.md
Validation scripts/validate_*.py
CI .github/workflows/validate.yml

Read the full file on GitHub · 82 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. 3d ago First seen · 82 lines · 539 tokens per session scan A e64c8b992fe4

Subscribe to this mod's changes

claude-plugins AGENTS.md is an instructions file published in the GitHub repository jontsai/claude-plugins (6 stars, last pushed 22d ago), licensed MIT. It adds 539 tokens to every session, about $0.0027 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.

Related

Other instructions, from other repositories