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/no-legacy-tool-surface.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/no-legacy-tool-surface)<a href="https://agentmods.dev/instructions/anselmoo/mcp-ai-agent-guidelines/no-legacy-tool-surface"><img src="https://agentmods.dev/badge/instructions/anselmoo/mcp-ai-agent-guidelines/no-legacy-tool-surface/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/no-legacy-tool-surface"><img src="https://agentmods.dev/badge/instructions/anselmoo/mcp-ai-agent-guidelines/no-legacy-tool-surface.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 | $0.00323 | $0.00323 |
| Opus 5 | $0.00161 | $0.00161 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
mcp-ai-agent-guidelines no-legacy-tool-surface.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 12d 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
No-Legacy Auxiliary Tool Surface Rules
When touching the auxiliary MCP tool surface, keep these constraints:
-
No command multiplexing
- Do not add or reintroduce
commandenums foragent-memory,agent-session, oragent-snapshot. - Keep granular tools only:
- memory:
agent-memory-read|write|fetch|delete - session:
agent-session-read|write|fetch|delete - snapshot:
agent-snapshot-read|write|fetch|compare|delete
- memory:
- Do not add or reintroduce
-
Persistence semantics must be explicit
*-writetools must return clear disk-persistence success/failure messages.- Include the target state directory in failure messages when possible.
-
Validation at tool boundary
- Tool inputs must be schema-validated using shared validators.
- Errors should be deterministic and actionable.
-
Backward compatibility policy
- Legacy monolithic aliases (
agent-memory,agent-session,agent-snapshot) are intentionally retired. - If referenced in docs/tests, update them to granular names.
- Legacy monolithic aliases (
-
Tests required for any surface changes
- Update
src/tests/tools/*and runtime MCP routing tests to match renamed tools. - Ensure no drift between listed tools and test coverage matrices.
- Update
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.
- 12d ago First seen · 31 lines · 323 tokens per session scan A 7ffc5c6cc44d
mcp-ai-agent-guidelines no-legacy-tool-surface.instructions.md is an instructions file published in the GitHub repository Anselmoo/mcp-ai-agent-guidelines (6 stars, last pushed today), licensed MIT. It adds 323 tokens to every session, about $0.0016 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
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
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.
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.