Borrowing it
Nothing to install: this file belongs to Anselmoo/mcp-ai-agent-guidelines. 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/Anselmoo/mcp-ai-agent-guidelines/main/.github/instructions/local-tool-safety.instructions.mdgit clone --depth 1 https://github.com/Anselmoo/mcp-ai-agent-guidelinesWrote 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/anselmoo/mcp-ai-agent-guidelines/local-tool-safety)<a href="https://agentmods.dev/instructions/anselmoo/mcp-ai-agent-guidelines/local-tool-safety"><img src="https://agentmods.dev/badge/instructions/anselmoo/mcp-ai-agent-guidelines/local-tool-safety/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/anselmoo/mcp-ai-agent-guidelines/local-tool-safety"><img src="https://agentmods.dev/badge/instructions/anselmoo/mcp-ai-agent-guidelines/local-tool-safety.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 | $0.00398 | $0.00398 |
| Opus 5 | $0.00199 | $0.00199 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
mcp-ai-agent-guidelines local-tool-safety.instructions.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 10d 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.
What it actually says
Local tool safety and workspace hygiene
This repository currently has unreliable local file creation and direct state deletion behavior. When working here, prefer safer project workflows and keep the local MCP server aligned with the latest build.
-
Avoid unsafe direct tool usage
- Do not use
fetch_webpagein this workspace unless there is no other way to get the data. - Do not call direct delete variants such as
agent-memory-deleteormcp_ai-agent-guid_agent-memory-delete. - Prefer explicit workspace edits,
agent-memory-read|write|fetch, andagent-session/read|writeflows instead.
- Do not use
-
Keep the local build current
- Before running or debugging anything in this repo, run
npm run build. - Restart the local MCP server after rebuilding so the agent uses the newest
dist/artifacts. - If local tools fail unexpectedly, rebuild and restart before changing the tool logic.
- Before running or debugging anything in this repo, run
-
Do not delete
.mcp-ai-agent-guidelines/manually- Avoid hard deleting the local state directory for troubleshooting.
- If the state directory needs to be reset, use the repository’s supported reset or onboarding workflows instead.
-
Coverage-first development
- New source files in
src/must ship tests and must not lower the project coverage rate. - Mirror new code under
src/tests/...and verify withnpm run test:coverage. - Add cases for both positive and negative branches in new logic.
- New source files in
-
Make diagnostics actionable
- When writing warnings or failure messages, call out the required recovery steps explicitly:
npm run build, restart the MCP server, and avoid unsafe direct delete tools. - Explain why the tool path is blocked, not just that it failed.
- When writing warnings or failure messages, call out the required recovery steps explicitly:
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.
- 10d ago First seen · 31 lines · 398 tokens per session scan A 18ff44c43b6d
mcp-ai-agent-guidelines local-tool-safety.instructions.md is an instructions file published in the GitHub repository Anselmoo/mcp-ai-agent-guidelines (6 stars, last pushed yesterday), licensed MIT. It adds 398 tokens to every session, about $0.0020 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
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.
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.
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).
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.