Borrowing it
Nothing to install: this file belongs to anatolykoptev/gtr-mcp. 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/anatolykoptev/gtr-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/anatolykoptev/gtr-mcpWrote 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/anatolykoptev/gtr-mcp/agents-md)<a href="https://agentmods.dev/instructions/anatolykoptev/gtr-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/anatolykoptev/gtr-mcp/agents-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/anatolykoptev/gtr-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/anatolykoptev/gtr-mcp/agents-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 | $0.01028 | $0.01028 |
| Opus 5.5 | $0.00411 | $0.00411 |
| Sonnet 5.5 | $0.00206 | $0.00206 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
gtr-mcp AGENTS.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 2mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gtr Worktree Agent Guide
This file teaches AI agents when and how to use git worktrees via the gtr-mcp MCP server.
Import it into your project's AGENTS.md or reference it in your system prompt.
Repo context
gtr-mcp operates on the git repository at the working directory it was launched in.
You do not pass a repo_path to any tool. The server is cwd-bound; the operator
sets the correct repository by configuring the MCP client's cwd field.
When to use a worktree
Use worktree_create when:
- Another agent holds main: a parallel agent is running tests or a deploy on the main checkout; you need to work without stepping on it
- Risky refactor: you want to make sweeping changes you might abandon; a worktree lets you switch back to main cleanly without stashing or reverting
- Parallel feature work: two independent features can progress simultaneously in separate worktrees without branch-switching overhead
- PR review: check out a PR branch in a worktree while your main branch stays at HEAD
Do NOT create a worktree for quick one-file edits — just work on the branch directly.
The standard loop
worktree_list → see what exists (source of truth, not agent memory)
worktree_create → spin up a new worktree
(work happens here via shell tools using the returned worktree_path)
worktree_status → check staged/unstaged/untracked
worktree_remove → clean up when done (requires confirm: true)
Source of truth
worktree_list is authoritative. Never assume a worktree exists because you created it earlier
in the session — always verify with worktree_list before acting on it.
Safety contract
worktree_remove and worktree_clean (with merged: true or closed: true) are DESTRUCTIVE.
They require confirm: true in the call:
{ "branch": "feature-x", "confirm": true }
Only pass confirm: true when the user has explicitly asked you to delete or clean worktrees.
When in doubt, use worktree_clean { "dry_run": true } to preview first.
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.
- 2mo ago First seen · 101 lines · 1,028 tokens per session scan A 17348621d24c
gtr-mcp AGENTS.md is an instructions file published in the GitHub repository anatolykoptev/gtr-mcp (0 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,028 tokens to every session, about $0.0041 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.
gtr-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gtr-mcp AGENTS.mdanatolykoptev/gtr-mcp | Instructions file | 0 | 4mo ago | Apache-2.0 | A | 1,028 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |