Borrowing it
Nothing to install: this file belongs to open-mcp-ai/termcp. 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/open-mcp-ai/termcp/main/AGENTS.mdgit clone --depth 1 https://github.com/open-mcp-ai/termcpWrote 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/open-mcp-ai/termcp/agents-md)<a href="https://agentmods.dev/instructions/open-mcp-ai/termcp/agents-md"><img src="https://agentmods.dev/badge/instructions/open-mcp-ai/termcp/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/open-mcp-ai/termcp/agents-md"><img src="https://agentmods.dev/badge/instructions/open-mcp-ai/termcp/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 | $0.01025 | $0.01025 |
| Opus 5.5 | $0.00410 | $0.00410 |
| Sonnet 5.5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
Termcp 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 today.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security & Privacy
禁止在项目中出现以下敏感信息和敏感文件：
- 本机 hostname、本地用户名称
- 真实密钥、API keys、tokens、passwords
- 邮箱地址、手机号等个人信息
- .env 文件、私钥文件（PEM、SSH key 等）
- 禁止出现
Co-Authored-By: Claude Opus 4.7 <[email protected]>相关字样 - 只有在人工同意后才能push和commit。在多次commit后，人工要求push再进行push，绝对不要主动push。
Agent skills
Issue tracker
Issues are tracked in GitHub Issues via gh CLI. See docs/agents/issue-tracker.md.
Triage labels
Default vocabulary: needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix. See docs/agents/triage-labels.md.
Domain docs
Project docs live under docs/ (docs/api.md, docs/architecture.md, docs/design/).
Releases
dev is the rebased development line; main only receives release PRs. Use
the process in docs/releasing.md before tagging. Write the ## Unreleased
notes before cutting the release — one short paragraph per user-visible
change since the last release, not a design note; make prepare-release only
moves them. Give the PR a release/vX.Y.Z head branch or release: vX.Y.Z
title, run make prepare-release RELEASE_VERSION=vX.Y.Z, and review the
generated changelog and server.json changes. CI checks both files before
merge.
A vX.Y.Z-rc.N tag is an internal test build: it adds a dated changelog
section, leaves server.json alone (no registry entry, no :latest move)
and is marked as a GitHub pre-release. Its branch and PR name the rc itself
(release/v0.2.8-rc.1), because CI requires the release signal to match the
files exactly — the final release is its own PR (release/v0.2.8).
docs/releasing.md has the details.
Tests run in CI on three OSes
Whenever you write or modify a test, remember it must pass in
.github/workflows/test.yml — ubuntu, macos and windows, via
go test ./... -count=1 -shuffle=on -race (make test locally, with a tighter
-timeout: CI widens it because a shared runner is several times slower, and a
run killed by -timeout names no failing test). For races the detector cannot
see — filesystem and lifecycle
races — run make test-stress locally before pushing. Assume concurrency, a
fresh runner, and dirty state from other tests or processes. Never hardcode a
shared absolute path; t.TempDir() is the default. See
docs/agents/testing.md.
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.
- today Changed · +2 lines · +29 tokens per session d13201227c38
- 2d ago Changed 88d463a70bb0
- 6d ago Changed · -1 lines · -9 tokens per session b2eef6429a54
- 8d ago Changed · +1 lines · +21 tokens per session a1a09e487e84
- 11d ago Changed · +11 lines · +180 tokens per session 45f13bec8fcb
- 20d ago Changed · +10 lines · +117 tokens per session 9f8cd81aeabc
- 1mo ago Changed · +9 lines · +100 tokens per session 7c6f4c5afe4b
- 1mo ago First seen · 48 lines · 587 tokens per session scan A 5ed6742c936a
Termcp AGENTS.md is an instructions file published in the GitHub repository open-mcp-ai/termcp (19 stars, last pushed 1mo ago), licensed MIT. It adds 1,025 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 2026-09-21.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.