Borrowing it
Nothing to install: this file belongs to bravew/trove. 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/bravew/trove/main/CLAUDE.mdgit clone --depth 1 https://github.com/bravew/troveWrote 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/bravew/trove/claude-md)<a href="https://agentmods.dev/instructions/bravew/trove/claude-md"><img src="https://agentmods.dev/badge/instructions/bravew/trove/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/bravew/trove/claude-md"><img src="https://agentmods.dev/badge/instructions/bravew/trove/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 | $0.01896 | $0.01896 |
| Opus 5.5 | $0.00758 | $0.00758 |
| Sonnet 5.5 | $0.00379 | $0.00379 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
trove 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 155 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.
What This Is
Trove — an open-source plugin marketplace for AI coding assistants. Plugins and skills are authored once and compiled to platform-specific formats for Claude Code, Cursor, OpenAI Codex, and a generic AGENTS.md fallback (Copilot/Windsurf/others).
Common Commands
bun install # Install dependencies
bun run build # Full 3-stage build (skills → plugins → marketplace)
bun run build:skills # Stage 1 only: resolve templates → SKILL.md
bun run build:plugins # Stage 2 only: assemble plugin manifests + copy skills
bun run build:marketplace # Stage 3 only: generate per-platform marketplace.json + catalog.json
bun run verify:generated # Build, then fail if it had to repair a committed artifact
bun run validate # Validate all structure, naming, frontmatter, secrets
bun run validate:plugins # Validate plugins only
bun run validate:market # Validate marketplace only
bun run validate:claude-manifests # claude plugin validate --strict, all plugins
bun run test:acceptance:setup # Installer link layout in a disposable HOME
bun run dev # Watch mode (rebuilds on change)
bun test # Run tests
# Scaffolding
bun run scaffold:plugin -- --name trove-testing --role dev
bun run scaffold:skill -- --plugin trove-dev --name trove-debug
# Importing external skills (see CONTRIBUTING.md and docs/upstream-sync.md)
bun run import:skill -- --inspect <git-url> --ref <sha> # Report only: license, selection, flags
bun run import:skill -- --stage <git-url> --id <name> --plugin <plugin> --category <dir> --mode vendored|adapted
/import-skill <git-url> --ref <sha> --id <name> --plugin <plugin> --category <dir> # Guided, in Claude Code
bun run sync:upstream -- --check --offline # Verify locks against local bytes, no network
bun run sync:upstream -- --check # Compare locks with upstream heads
# Evals
bun run eval:gate # Quality gate (CI blocker on main)
bun run eval:changed # Eval only changed skills
# CLI
./bin/trove search "security"
./bin/trove list --role=dev
./bin/trove info trove-dev
# Release
bun run bump-version # Auto-bump VERSION file
bun run promote-stable # Promote canary to stable
# Setup (installs to detected hosts)
./setup # Auto-detect Claude/Cursor/Codex/OpenCode/Gemini
./setup --host claude # Claude Code only
./setup --host opencode # OpenCode only
./setup --host gemini # Gemini CLI only
./setup --role dev # Developer plugins only
./setup --uninstall # Remove every link the installer created
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.
- 1mo ago Changed · +7 lines · +159 tokens per session 9c3ff0202272
- 2mo ago Changed · +1 lines · +31 tokens per session 45d2d9308e9a
- 2mo ago First seen · 147 lines · 1,706 tokens per session scan A b214c3135853
trove CLAUDE.md is an instructions file published in the GitHub repository bravew/trove (10 stars, last pushed today), licensed MIT. It adds 1,896 tokens to every session, about $0.0076 per session on Opus 5.5. 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.
trove CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trove CLAUDE.mdbravew/trove | Instructions file | 10 | today | MIT | A | 1,896 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |