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/bearlike/grove/claude-mdgit clone --depth 1 https://github.com/bearlike/GroveWrote 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/bearlike/grove/claude-md)<a href="https://agentmods.dev/instructions/bearlike/grove/claude-md"><img src="https://agentmods.dev/badge/instructions/bearlike/grove/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 | $0.05997 | $0.05997 |
| Opus 5 | $0.02998 | $0.02998 |
| Sonnet 5 | $0.01199 | $0.01199 |
| Haiku 4.5 | $0.00600 | $0.00600 |
Grade D, and why
Grove CLAUDE.md scanned grade D with 3 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **Never run a Grove entrypoint as root — it poisons the editable install, and uv's error never says so.** The `uv tool` venv and (editable install ⇒) the checkout's `src/grove/**/__pycache__` are user-owned; one root-r Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- **A Grove workspace is a git worktree, so it sees only committed files.** Uncommitted working-tree edits never propagate into a worktree — commit shared config (e.g. `.mcp.json`, whose tokens are env refs, not literals Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Never run a Grove entrypoint as root — it poisons the editable install, and uv's error never says so.** The `uv tool` venv and (editable install ⇒) the checkout's `src/grove/**/__pycache__` are user-owned; one root-r How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grove — Agent Guide
Grove lets you tend multiple git worktrees like branches in a forest: spin up, switch between, and tear down isolated coding sessions without losing your place. See README.md for the product brief.
Handling a handed-off issue (the autonomous workspace loop)
When you own a tracker issue end-to-end, drive it to a merged PR on this loop. Bias to action — never over-plan, over-spec, ask trivial questions, or invent fallbacks nobody requested.
- Read the issue, map the components, implement. Read the nearest owning
CLAUDE.md(s) on the path you'll touch before editing. - Keep the issue number OUT of the PR title and body. PR text and squash titles mirror to the public GitHub remote, where a bare
#<n>resolves against a different tracker — soFixes #<n>would both leak the private issue graph and auto-close nothing. - Check the open PR for conflicts with the remote target and resolve them — rebase onto the freshly-fetched target, re-apply onto the current structure (don't clobber what landed meanwhile), re-run the gates, force-push.
- Reply on the issue naming the PR — that comment IS the linkage, since the PR carries none. Summarize the design decision, the components touched, and the gate results. Say plainly anything that did not work, anything left out, and any acceptance criterion that turned out to be unsatisfiable — a ticket whose own premise was wrong is the most valuable thing you can leave behind, and the next session cannot recover it from the diff. Close the issue by hand once the PR merges: an open ticket with a linked PR is honest, a closed one with unmerged work is not.
- After implementing, fold the durable insights into the nearest owning
CLAUDE.md— the invariant, the trade-off, the reference you'd otherwise re-derive; never copyable snippets or restatements of code.
Parallelize — fan a fleet of sub-agents out over disjoint work per the parallel-agent pattern below.
Core operating rules
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.
- 3d ago First seen · 130 lines · 5,997 tokens per session scan D ee78375f7fa0
Grove CLAUDE.md is an instructions file published in the GitHub repository bearlike/Grove (2 stars, last pushed 13d ago), licensed MIT. It adds 5,997 tokens to every session, about $0.0300 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, reads mcp configuration, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
super-fr AGENTS.md
AGENTS.md instructions for derio-net/super-fr, covering agent instructions — super-fr, repo shape, dev commands, skills/rules: canonical source vs. generated mirrors and this repo dogfoods fr-isolation on itself.
super-fr CLAUDE.md
Claude Code instructions for derio-net/super-fr, a project described as: Claude Code plugin suite: superpowers-wrapped planning, devcontainer+worktree isolation, goal-to-PR autonomy, and phase dispatch to VibeKanban runners.
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.
my-claude-skills CLAUDE.md
Instructions for brody-0125/my-claude-skills, covering claude code skills repository, validation commands, sub-kopring-engineer: kotlin/java 코드 컨벤션 검증, numerical: 수치 연산 코드 검증 and sub-test-engineer: 문서 일관성 검증.