recompose

Agent settings that enable several plugins and an MCP server, a tool connection for external project services, along with commands that protect sensitive or generated files.

In plain words
What is it for?
They are for enabling the listed Codex, Superpowers, Karpathy, Ponytail, Storybook, and Mobbin integrations, and blocking edits to files such as `.env`, certificates, keys, and `pnpm-lock.yaml`.
Why use it?
They configure extra development tools while preventing accidental edits to lockfiles, environment secrets, and private key material.

Settings file for Claude Code

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 settings/recomposesh/recompose/settings
Clone the repo
git clone --depth 1 https://github.com/recomposesh/recompose

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

recompose 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/settings.json · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "enableAllProjectMcpServers": true,
  "enabledMcpjsonServers": [
    "mobbin"
  ],
  "enabledPlugins": {
    "codex@openai-codex": true,
    "superpowers@claude-plugins-official": true,
    "andrej-karpathy-skills@karpathy-skills": true,
    "ponytail@ponytail": true,
    "storybook@storybook": true
  },
  "extraKnownMarketplaces": {
    "ponytail": {
      "source": {
        "source": "github",
        "repo": "DietrichGebert/ponytail"
      }
    },
    "storybook": {
      "source": {
        "source": "github",
        "repo": "storybookjs/mcp",
        "ref": "main"
      }
    }
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "f=$(jq -r '.tool_input.file_path // empty'); case \"$f\" in *pnpm-lock.yaml) echo 'pnpm-lock.yaml is generated - run pnpm commands instead of editing it' >&2; exit 2;; *.env.example) ;; *.env|*.env.*) echo '.env files hold secrets - the user edits these by hand' >&2; exit 2;; *.pem|*.key|*.p12|*/id_rsa*|*/id_ed25519*) echo 'key material is never edited by Claude' >&2; exit 2;; esac"
          }
        ]
      },
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "c=$(jq -r '.tool_input.command // empty'); case \"$c\" in *--no-verify*|*--no-gpg-sign*) echo 'hook bypass flags are blocked - fix the failing gate instead of skipping it' >&2; exit 2;; esac"
          }
        ]
      },
      {
        "matcher": "Edit|Write|NotebookEdit",
        "hooks": [
          {
            "type": "command",
            "command": "node \"${CLAUDE_PROJECT_DIR}/.claude/workflows/hooks/launch-gate.mjs\"",
            "timeout": 120,
            "statusMessage": "test-first gate"
          }
        ]
      }
    ],
    "PostToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "node

Read the full file on GitHub · 74 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 · 74 lines scan A 8f3da21a3270

Subscribe to this mod's changes

recompose is a settings file published in the GitHub repository recomposesh/recompose (24 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.