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.
npx agentmods add instructions/bravew/trove/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.svg" alt="Measured on agentmods" 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 | $0.01706 | $0.01706 |
| Opus 5 | $0.00853 | $0.00853 |
| Sonnet 5 | $0.00341 | $0.00341 |
| Haiku 4.5 | $0.00171 | $0.00171 |
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 5d 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 — 147 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 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
# 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.
- 5d 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 7d ago), licensed MIT. It adds 1,706 tokens to every session, about $0.0085 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.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).