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/johnlindquist/mdflow/claude-mdgit clone --depth 1 https://github.com/johnlindquist/mdflowWhat 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 | $0.08625 | $0.08625 |
| Opus 5 | $0.04313 | $0.04313 |
| Sonnet 5 | $0.01725 | $0.01725 |
| Haiku 4.5 | $0.00863 | $0.00863 |
Grade A, and why
mdflow 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 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 — 599 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Overview
mdflow (md) is a CLI tool that executes AI agents defined as markdown files. It parses YAML frontmatter for configuration and passes keys directly as CLI flags to the specified command (claude, codex, gemini, copilot, or any other CLI tool).
CLI Subcommands
md <file.md> [flags] # Run a flow (bare `md` opens the Flow Workbench)
md doctor [--json] # Inspect project readiness and safe next actions, no execution (free)
md init [--guided] [-e <eng>] [-y] [--agents] [--print-guide]
# Scaffold a starter roster (deterministic, zero engine
# turns; --guided runs the interactive setup session)
md create [name] # Create a flow and a fail-closed draft eval suite
md capture # Print the guide an in-session agent follows to capture
# the current conversation as a flow (free; see src/capture.ts)
md explain <flow.md> [--json] # Show resolved config without executing (free)
md render <flow.md> # Inspect, write, or open a rendered flow explanation
md hooks add|list|remove <flow.md> [event…] # Manage the flow's lifecycle hooks file (free)
md eval <flow.md> # Run the flow's eval suite (costs engine turns; --plan is free)
md eval add|list|remove|coverage # Scaffold/manage suites, fail-closed verdicts, CI ratchet (free)
md feedback <flow.md> "msg" # Record durable evolution evidence (free; `md complain` is an alias)
md evolve plan|propose|show|apply <flow.md|run-id> # Proposal-first evolution (plan is free)
md install <url|gh:...> # Install a flow into the registry (see src/registry.ts)
md remove <name> # Remove an installed registry flow
md list # List installed registry flows
md roster [sync] [--agents] [--json] # Inspect flows / sync the managed operator card
md catalog [--json] # Machine-readable catalog of every discoverable flow
md setup # Configure shell (PATH, aliases)
md logs # Show flow log directory
md help # Show help
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 · 599 lines · 8,625 tokens per session scan A be2f64fd1497
mdflow CLAUDE.md is an instructions file published in the GitHub repository johnlindquist/mdflow (603 stars, last pushed 2d ago), licensed MIT. It adds 8,625 tokens to every session, about $0.0431 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 2026-08-30.
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.