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/fallow-rs/fallow/claude-mdgit clone --depth 1 https://github.com/fallow-rs/fallowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/fallow-rs/fallow/claude-md)<a href="https://agentmods.dev/instructions/fallow-rs/fallow/claude-md"><img src="https://agentmods.dev/badge/instructions/fallow-rs/fallow/claude-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00370 | $0.00370 |
| Opus 5 | $0.00185 | $0.00185 |
| Sonnet 5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
fallow 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 4d 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
Fallow repository adapter for Claude
Fallow is a Rust-native codebase analyzer for JavaScript and TypeScript.
@AGENTS.md @docs/README.md
Both files above are imported: the universal repository contract for Claude,
Codex, and contributors, and the central documentation index. Read
docs/development/task-context-map.md next to load only the references the
current task needs.
Knowledge layers
.agents/skills/is the canonical, client-neutral maintainer workflow tree..claude/skills/is generated from.agents/skills/. Never edit it by hand..claude/rules/contains only Claude-specific, path-scoped constraints.docs/contains durable public maintainer architecture and references..plans/is gitignored task state. Promote durable decisions into indexed public documentation.
Workflow
Use the native lifecycle for non-trivial work:
implementpanel-reviewwhen the change has design or user-facing decisionsreviewshipsweep
The controlling workflow lives in the matching .agents/skills/<name>/SKILL.md.
Do not layer unrelated workflow systems onto this lifecycle.
Trust boundary
This public repository must contain only public OSS knowledge and contracts. Private cloud architecture, operations, customers, commercial context, and incidents belong in the private cloud repository. Public behavior may be documented here or in the public user documentation repository, but private prose must never be copied or automatically exported.
Generated surfaces
Run npm run generate:contracts:check and
npm run check:agent-adapters after changing public contracts or skills.
Generated files identify their source and must not be edited directly.
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.
- 4d ago First seen · 48 lines · 370 tokens per session scan A c4d77e53e5ce
fallow CLAUDE.md is an instructions file published in the GitHub repository fallow-rs/fallow (4,438 stars, last pushed yesterday), licensed MIT. It adds 370 tokens to every session, about $0.0019 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
oxc AGENTS.md
Instructions for oxc-project/oxc, covering agents.md - ai assistant guide for oxc, ai usage policy for contributors, repository structure, core crates and development commands.
biome AGENTS.md
Instructions for biomejs/biome, covering agent guidelines for contributing to biome, communication, before editing, implementation gate and final review.
oxc copilot-instructions.md
Instructions for oxc-project/oxc: When reviewing pull requests in this repository.
static-analysis AGENTS.md
Instructions for analysis-tools-dev/static-analysis, covering guidelines for ai agents and assistants and 🤖 instructions for the ai.
biome CLAUDE.md
Instructions for biomejs/biome, a project described as: A toolchain for web projects, aimed to provide functionalities to maintain them. Biome offers formatter and linter, usable via CLI and LSP.
truecourse CLAUDE.md
Instructions for truecourse-ai/truecourse, covering truecourse — claude instructions, key files to keep updated, project layout, development commands and storage.