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/cofin/flow/claude-mdgit clone --depth 1 https://github.com/cofin/flowWhat 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 | $0.00131 | $0.00131 |
| Opus 5 | $0.00066 | $0.00066 |
| Sonnet 5 | $0.00026 | $0.00026 |
| Haiku 4.5 | $0.00013 | $0.00013 |
Grade A, and why
flow 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.
What it actually says
Flow for Claude Code
Flow is a skill, not a CLI. In repositories with .agents/, invoke the Flow
skill or a /flow:* command.
Route requests through the Flow router. Planning and
task state live under .agents/bundles/specs/<flow_id>/; task worksheets are
authoritative. Apply lifecycle mutations through
the state contract.
Use /flow:* commands for lifecycle requests. Preserve unrelated work, stage
exact paths, never mutate tags, and require fresh user permission before pushes
or hosted repository writes.
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 · 14 lines · 131 tokens per session scan A 94ad3e2de95b
flow CLAUDE.md is an instructions file published in the GitHub repository cofin/flow (15 stars, last pushed 3d ago), licensed Apache-2.0. It adds 131 tokens to every session, about $0.0007 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
scaffold AGENTS.md
Instructions for zigrivers/scaffold, covering agent instructions, quick reference, scaffold releases and landing the plane (session completion).
foolery CLAUDE.md
Instructions for acartine/foolery, covering agent instructions, codex configuration, repository overrides, git worktree policy (hard override) and worktree dependency bootstrap.
foolery AGENTS.md
Instructions for acartine/foolery, covering agent instructions, codex configuration, repository overrides, git worktree policy (hard override) and worktree dependency bootstrap.
looper_rust AGENTS.md
Instructions for quangdang46/looper_rust, covering looper rust — ai agent guidelines, build, test, lint and workspace members.
bd-explore GEMINI.md
Gemini CLI instructions for halaprix/bd-explore, covering gemini.md - gemini / antigravity guide for bd-explore, context & guidelines, running verification tests and structure.
scaffold CLAUDE.md
Instructions for zigrivers/scaffold, covering claude.md, core principles, project overview, structure and source of truth.