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/claude-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 | $0.05697 | $0.05697 |
| Opus 5 | $0.02848 | $0.02848 |
| Sonnet 5 | $0.01139 | $0.01139 |
| Haiku 4.5 | $0.00570 | $0.00570 |
Grade A, and why
mcp CLAUDE.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 — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp repo — Claude conventions
Project-wide guidance for Claude (and any other agent) working in this repo. Read this before opening files; the rules below are load-bearing.
Rendering surface — chat-native markdown + host-native widgets
The Leadbay MCP server does not ship any custom widgets. We tried
the MCP Apps _meta.ui.resourceUri path through 0.10.0-dev.10 — six
widget packages, full Vite build pipeline, ext-apps SDK. It failed for
two structural reasons:
- Iframes don't blend with chat. Chat hosts rendered our widgets as bright sandboxed rectangles in the dark chat thread. MCP Apps's theme variables weren't reliably injected, and even when they were, iframes can't visually flow with markdown bubbles.
- They short-circuited host-native rendering. When our widget
auto-rendered, the LLM stopped routing to richer first-party widgets
(
places_map_display_v0,ask_user_input_v0,message_compose_v1) because the job felt done.
So tools render via two surfaces only:
| Surface | What it covers |
|---|---|
| Chat-native markdown (default) | The canonical RENDERING blocks every tool description carries — markdown tables, cards, chips, headings. Inherits the chat's theme, font, link styling for free. Dark-mode-aware on every host. |
| Host-native widgets (when the host exposes them) | Claude's three first-party widgets — places_map_display_v0 for maps, message_compose_v1 for outreach drafts, ask_user_input_v0 for NEXT STEPS / clarifications. ChatGPT exposes the same routing pattern via _meta.openai/outputTemplate. |
Do not re-introduce Tool.ui bindings. The field was removed from
the Tool interface in 0.10.0-dev.12. Re-adding it would resurrect the
iframe-vs-chat structural problem.
The three host-native widgets
Every tool whose result fits one of these shapes carries a RENDER
directive naming the widget. Field maps + constraints live in
packages/promptforge/snippets/gates/builtin-widgets.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.
- yesterday First seen · 533 lines · 5,697 tokens per session scan A c06740b5988e
mcp CLAUDE.md is an instructions file published in the GitHub repository leadbay/mcp (0 stars, last pushed yesterday), licensed MIT. It adds 5,697 tokens to every session, about $0.0285 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
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 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).
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.
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 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).
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.