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/leadbay/mcp/agents-mdgit clone --depth 1 https://github.com/leadbay/mcpWhat 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 | $0.00851 | $0.00851 |
| Opus 5 | $0.00426 | $0.00426 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
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 yesterday.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — leadbay/mcp
Guidance for AI agents (OpenAI Codex, etc.) working in this repo.
Full engineering conventions live in CLAUDE.md; the
canonical map of user intent → MCP assets → tests is
WORKFLOWS.md. Read those before making non-trivial
changes. This is a pnpm monorepo (pnpm 10, Node ≥22); core is the
shared library and mcp is the stdio server that exposes it.
Review guidelines
Codex reads this section for automated PR reviews. Flag the following as high-priority (P0/P1) issues:
-
Never hand-edit generated files.
packages/core/src/tool-descriptions.generated.tsandpackages/mcp/src/prompts.generated.tsare emitted by@leadbay/promptforgefrom.md.tmplsources underpackages/promptforge/{tool-descriptions,prompts,snippets}/. Any diff that edits a*.generated.*file directly will be wiped on the next build — flag it and point to the template. -
Do not re-introduce
Tool.uibindings or MCP-Apps iframe widgets. TheTool.uifield was removed in 0.10.0-dev.12. Rendering is chat-native markdown plus the three host-native widgets only (places_map_display_v0,message_compose_v1,ask_user_input_v0). -
Respect the tool-description char budget. Composites cap at ~16k chars, hard cap 17k, enforced by
packages/mcp/test/audit/tool-description-source.test.ts. Flag edits that risk the cap — and never "fix" a failing audit by disabling or weakening it; trim the template body instead. -
New user-facing tools must be wired completely. They must declare
routingandrendering_hintfrontmatter (plusnext_stepswhen the tool has a NEXT STEPS table), be added toTOOLS_WITH_ROUTINGinpackages/mcp/test/audit/routing-block.test.ts, and carry ≥2 positive AND ≥2 negative routing examples. Everyroute_toanti-trigger must resolve to a registered tool name. -
WORKFLOWS.mdis normative. A new user story needs a row, and every backtick-wrappedleadbay_*identifier must resolve to a registered tool/prompt/skill (checked bypackages/mcp/test/audit/workflows.test.ts).
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.
- yesterday First seen · 64 lines · 851 tokens per session scan A 77e396950abe
mcp AGENTS.md is an instructions file published in the GitHub repository leadbay/mcp (0 stars, last pushed yesterday), licensed MIT. It adds 851 tokens to every session, about $0.0043 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
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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
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.