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/dastholo/lean-md/agents-mdgit clone --depth 1 https://github.com/dasTholo/lean-mdWhat 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 | $0.01503 | $0.01503 |
| Opus 5 | $0.00751 | $0.00751 |
| Sonnet 5 | $0.00301 | $0.00301 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
lean-md 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lean-md — Macro/Directive Markdown Renderer
lean-md is a standalone crate (lib lean_md + bin lean-md) distributed as a
lean-ctx addon. Its render core (rushdown + evalexpr) runs in-process and
needs zero lean-ctx. Every code-intel directive is outbound over the
MCP/CLI wire via backend::CodeIntelBackend (CLI default, MCP opt-in) — lean-md
holds no lean_ctx crate dependency (only lean-ctx-client, behind the
mcp feature).
Integration Mode: Hybrid (for developing THIS repo)
When working on lean-md itself, prefer lean-ctx tooling for token savings:
- Reads/Search → MCP tools (
ctx_read,ctx_search) for caching + compression - Shell commands →
lean-ctx -c "…"via CLI (preferred) orctx_shellvia MCP - File editing → anchored loop
ctx_read(mode=anchored)→ctx_patch(default, patch by LINE:HASH anchor);ctx_editonly tiny-span/replace-all; symbol nav/refactor/reformat viactx_refactor; symbol body by name viactx_search action=symbol
MCP tools
| Tool | Purpose |
|---|---|
ctx_read(path, mode) |
Cached, compressed file reads (10 modes) |
ctx_search(pattern, path) |
Token-efficient code search |
ctx_shell(command) |
Compressed shell output (alternative to CLI) |
ctx_patch(path, anchor) |
Anchored edit (default): patch by LINE:HASH from ctx_read(mode=anchored) |
ctx_edit(path, old, new) |
str_replace fallback — tiny-span / replace-all |
ctx_refactor |
LSP/PSI symbol nav, refactor engine, action=reformat (pre-commit) |
CLI commands (optimized shell, lower overhead)
lean-ctx -c "git status" # compressed shell output
lean-ctx -c "cargo nextest run" # compressed test output
lean-ctx ls src/ # directory map
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.
- 2d ago First seen · 119 lines · 1,503 tokens per session scan A c2adf4cd2642
lean-md AGENTS.md is an instructions file published in the GitHub repository dasTholo/lean-md (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,503 tokens to every session, about $0.0075 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
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.
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.