What is claude-code-plugins AGENTS.md?

Repository instructions for a Claude Code plugin marketplace, covering plugin structure, development conventions, tests, validation, and where project files belong.

Use them when building plugins, editing marketplace metadata, running tests, validating a plugin, or checking Claude Code plugin behaviour.

They reduce uncertainty when adding or updating plugins and point to the checks needed to catch missing marketplace entries or broken changes.

claude-code-plugins AGENTS.md — Instructions file by bengous

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/bengous/claude-code-plugins/agents-md

Clone the repo

git clone --depth 1 https://github.com/bengous/claude-code-plugins

Made for: Codex, OpenCode.

Per session 1,075 This file is loaded in full into every session.

When invoked 1,075 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.

Model	Per session	Once invoked
Fable 5	$0.01075	$0.01075
Opus 5	$0.00537	$0.00537
Sonnet 5	$0.00215	$0.00215
Haiku 4.5	$0.00108	$0.00108

Measured yesterday against content hash 1ce3155963f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-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 yesterday.

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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Plugin Marketplace

One directory per plugin, listed in .claude-plugin/marketplace.json.

Plugin Work

Do not reinvent plugin patterns. Delegate:

/plugin-dev:create-plugin and the plugin-dev skills (structure, skills, hooks, agents, settings) to build or modify a plugin
plugin-dev:plugin-validator agent to validate one
claude-code-guide agent for Claude Code behavior questions
Live doc search: the claude-code-docs MCP server (user scope, https://code.claude.com/docs/mcp)
Official docs, the fallback when those are not installed: https://code.claude.com/docs/en/plugins

New plugin: add its marketplace.json entry and its README.md table row by hand; no check catches their absence. Version bumps: edit plugin.json only; pre-commit propagates to the existing entry and row.

Testing a plugin from source (launch flags, permission modes, transcript checks): docs/plugin-testing.md.

Commands

bun test                                               # every suite outside dot directories
bun test ./.claude/hooks/*.test.ts                     # the repo's own hooks; `bun test` skips them
bun ./scripts/validate-marketplace.ts                  # versions + structure
bun ./scripts/validate-frontmatter.ts --all            # frontmatter (default: staged only)
bun x tsgo --noEmit                                    # types; fall back to ./node_modules/.bin/tsc --noEmit if tsgo rejects a flag
bun x oxlint                                           # lint (correctness + suspicious + pedantic + anti-slop)
bun x oxfmt '**/*.ts' '**/*.js' '**/*.mjs' '**/*.cjs'  # format; add --check to verify only
bun ./scripts/lint-shell.ts                            # shellcheck + shfmt; takes paths, else the whole repo

Everything above also runs in pre-commit and CI except bun test: lefthook.yml declares no test job, so run the tests yourself before pushing. Job list, order, and argument differences: docs/repo-ops.md.

Code Standards

Read the full file on GitHub · 71 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.

yesterday First seen · 71 lines · 1,075 tokens per session scan A 1ce3155963f3

Subscribe to this mod's changes

claude-code-plugins AGENTS.md is an instructions file published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 1,075 tokens to every session, about $0.0054 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.

Productivity Testing automation claude-code developer-tools workflow

claude-code-plugins AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Claude Code Plugin Marketplace

Plugin Work

Commands

Code Standards

What this file has done since we first saw it

Other instructions, from other repositories

workflowbuilder CLAUDE.md

WorkFlowX CLAUDE.md

STAR AGENTS.md

airflow CLAUDE.md

usurahi CLAUDE.md

gza CLAUDE.md