What is swe-marketplace CLAUDE.md?

Repository instructions for a public Claude Code plugin marketplace: a catalogue lists the plugins, while each plugin contains its own agents, skills, commands, and generated manifest.

Use them when editing marketplace or plugin files, generating manifests, checking for drift, validating plugins, or understanding the repository layout.

They explain which files are authoritative, which files are generated, and how to avoid catalogue and plugin metadata drifting apart.

How andisab/swe-marketplace configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to andisab/swe-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.

Copy the file

curl -O https://raw.githubusercontent.com/andisab/swe-marketplace/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/andisab/swe-marketplace

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/andisab/swe-marketplace/claude-md/github.svg)](https://agentmods.dev/instructions/andisab/swe-marketplace/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/andisab/swe-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/andisab/swe-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/andisab/swe-marketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/andisab/swe-marketplace/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,081 This file is loaded in full into every session.

When invoked 1,081 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.01081	$0.01081
Opus 5	$0.00541	$0.00541
Sonnet 5	$0.00216	$0.00216
Haiku 4.5	$0.00108	$0.00108

Measured 10d ago against content hash b9207f47eec3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

swe-marketplace 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 10d 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Context for Claude working in this repo. User-facing docs live in README.md.

What this repo is

Public Claude Code plugin marketplace. 13 plugins under plugins/<name>/, indexed by a single catalog at .claude-plugin/marketplace.json.

Repo layout

.claude-plugin/marketplace.json   # catalog — source of truth for all plugin metadata
plugins/<name>/
  .claude-plugin/plugin.json      # GENERATED from marketplace.json (do not hand-edit)
  agents/                         # YAML-frontmatter markdown
  skills/                         # subdirs, each a skill
  commands/                       # markdown
  README.md
scripts/
  synthesize-plugin-manifests.py  # generator (writes; --check fails on drift)
  validate-all.sh                 # runs `claude plugin validate` on catalog + every plugin
.github/workflows/validate-plugins.yml  # CI drift guard

Tree command: eza -TL 2 --icons --git-ignore

Dual-manifest convention (added in commit a673778, 2026-05-04)

Two manifests ship together:

.claude-plugin/marketplace.json — catalog used by /plugin marketplace add + /plugin install. Source of truth.
plugins/<name>/.claude-plugin/plugin.json — per-plugin manifest. Required by SDK consumers that load plugins directly via ClaudeAgentOptions.plugins=[{"type":"local","path":...}] / CLI --plugin-dir. Without it, those consumers silently fail to register skills/commands/hooks.

The two are kept in sync by a generator. Marketplace.json is the only file you edit.

Field rules (enforced by the generator)

plugin.json = the matching marketplace.json entry minus source, category, strict (those are marketplace-only; claude plugin validate warns on them in plugin.json).

Verbatim from marketplace entry: name, version, description, author, homepage, repository, license, keywords, agents, skills, commands, hooks, mcp, dependencies.

Required formats (per claude plugin validate):

agents: file paths — ["./agents/foo.md"], not parent dirs.
skills: subdir paths — ["./skills/coordinator"].
commands / hooks: file paths.
repository: string URL, not {type, url}.
author: object {name, email?, url?}, not bare string.
dependencies: array of plugin names, not version-pinned object map.

Read the full file on GitHub · 93 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.

10d ago First seen · 93 lines · 1,081 tokens per session scan A b9207f47eec3

Subscribe to this mod's changes

swe-marketplace CLAUDE.md is an instructions file published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed 22d ago), licensed MIT. It adds 1,081 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 2026-08-30.

Building agents Claude Code ai-assisted-development anthropic anthropic-claude claude-code-plugin marketplace

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

swe-marketplace: Instructions file for Claude Code