A set of instructions for analyzing TypeScript and JavaScript codebases with a Rust-native analyzer called Fallow. It also points to the project's documentation and development workflows.

Use it when navigating or reviewing a Fallow codebase, especially before implementing, reviewing, or shipping changes.

It gives the agent a consistent route through repository guidance, quality checks, reviews, and shipping steps. This reduces reliance on undocumented local files.

fallow — Instructions file by fallow-rs

Install

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.

agentmods

npx agentmods add instructions/fallow-rs/fallow/agents-md

Clone the repo

git clone --depth 1 https://github.com/fallow-rs/fallow

Made for: Codex, OpenCode.

Per session 1,127 This file is loaded in full into every session.

When invoked 1,127 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01127	$0.01127
Opus 5	$0.00563	$0.00563
Sonnet 5	$0.00225	$0.00225
Haiku 4.5	$0.00113	$0.00113

Measured 2d ago against content hash b8ec81528bb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fallow 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.

AGENTS.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fallow agent guide

This file is the tracked, always-loaded router for Codex. Keep it short. Durable architecture, validation, and review knowledge belongs under docs/, while repeatable workflows belong under .agents/skills/.

Start here

Read docs/README.md for the maintained documentation map.
Use docs/development/task-context-map.md to load only the references required for the task.
Load the matching workflow from .agents/skills/<name>/SKILL.md.
Follow nested AGENTS.md files when working in a scoped subsystem.

The shared development references are:

Do not rely on .codex/skills, sibling checkouts, private symlinks, or machine-local files. A fresh clone must contain everything required by these routes.

Workflow

Fallow's native lifecycle is authoritative:

implement -> panel-review -> review -> ship -> sweep

Use the corresponding tracked skills under .agents/skills/. Codex consumes that canonical tree directly. Claude adapters under .claude/skills/ are generated and must pass npm run check:agent-adapters.

Before editing, check the current branch and worktree. Other agents may be working in the same checkout. Re-read files immediately before editing, keep changes narrowly scoped, and never revert unrelated work.

Architecture

The analysis pipeline is:

config -> discovery -> extract -> resolve -> graph -> analyze -> output

Use docs/development/repo-map.md for crate ownership and high-value paths. Important invariants:

Fallow performs syntactic analysis with Oxc, without the TypeScript compiler.
Use FxHashMap and FxHashSet instead of the standard hash collections.
Re-export chains and workspaces are first-class graph concerns.
JSON, SARIF, CodeClimate, LSP, MCP, and editor output are public contracts.
LSP and MCP should remain thin integration layers over shared analysis.

Read the full file on GitHub · 129 lines

Changes

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 · 129 lines · 1,127 tokens per session scan A b8ec81528bb6

Subscribe to this mod's changes

fallow is an instructions file published in the GitHub repository fallow-rs/fallow (4,438 stars, last pushed today), licensed MIT. It adds 1,127 tokens to every session, about $0.0056 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.

Languages cli code-quality dead-code developer-tools javascript linter

fallow

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Fallow agent guide

Start here

Workflow

Architecture

What this file has done since we first saw it

Other instructions, from other repositories

oxc AGENTS.md

biome AGENTS.md

oxc copilot-instructions.md

static-analysis AGENTS.md

biome CLAUDE.md

truecourse CLAUDE.md