agentmods.dev

formax AGENTS.md

Repository instructions for the Formax coding project. They describe where major parts of the TypeScript code live, how the project is organized, how to build and test it, and the expected coding style.

In plain words
What is it for?
Use them when working on Formax's CLI, terminal UI, runtime setup, tools, streaming code, subagents, tests, or related project structure.
Why use it?
They give contributors a reliable starting point so they can find the right files and follow the project's established development rules.

Instructions file for CodexOpenCode

192 +1 1mo ago A scan 3,468 tokens original MIT
View the source file yusifeng/formax
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/yusifeng/formax/agents-md
Clone the repo
git clone --depth 1 https://github.com/yusifeng/formax

Made for: Codex, OpenCode.

Per session 3,468 This file is loaded in full into every session.
When invoked 3,468 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.

ModelPer sessionOnce invoked
Fable 5 $0.03468 $0.03468
Opus 5 $0.01734 $0.01734
Sonnet 5 $0.00694 $0.00694
Haiku 4.5 $0.00347 $0.00347

Measured 3d ago against content hash af0ab1e324d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

formax 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 3d 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 · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

AGENTS Scope

  • Keep high-frequency operational guidance here (review workflow/profile, commonly used commands/scripts, commit workflow, and day-to-day guardrails).
  • Keep canonical product/runtime semantics in docs/contracts/* and related canonical docs.
  • Keep code navigation in CODEMAP.md ("where to change what"), with AGENTS linking to it instead of duplicating path-level maps.

Project Structure & Module Organization

  • packages/core/src/ contains TypeScript source.
    • entrypoints/ CLI/runtime entrypoints (for example cli.tsx).
    • runtime/cli/ argument parsing + command dispatch for the CLI wrapper.
    • runtime/bootstrap/ REPL bootstrap + runtime assembly wiring.
    • core/ productized app core (config resolution, setup flows, boundaries checks).
    • tui/ Ink “wizard” UIs (first-run setup, selectors, forms).
    • adapters/ filesystem + setup adapters (config files, setup persistence).
    • screens/ Ink screens; components/ reusable UI.
    • tools/ tool registry, modules, handlers, presenters, runtime managers.
    • streaming/ Anthropic streaming client and parsers.
    • features/subagents/ registry/runner for sub-agent tools.
    • prompts/, config/, services/, shared/utils/ supporting code.
  • packages/ contains companion workspaces. Package-local implementation details belong to each package AGENTS.md.
  • Tests live next to source as *.test.ts/*.test.tsx.
  • docs/ holds architecture notes and guides; plans/ captures refactor plans.
  • proxy/ contains proxy/logger scripts plus traffic/log artifacts used for parity/reference during development.
  • CODEMAP.md is the “where to change what” index (entrypoints, main loop, tools, plan mode, sub-tasks).

Build, Test, and Development Commands

  • bun install installs dependencies.
  • bun run dev runs the CLI via tsx (entry: packages/core/src/entrypoints/cli.tsx).
  • bun run app-server:bridge -- --host 127.0.0.1 --port 3777 runs the app-server WebSocket bridge for web client development.
  • bun run build bundles the CLI to dist/cli.js (requires Bun).
  • bun run type-check runs TypeScript checks + boundary checks (core + ui).
  • bun run check:root-script-governance enforces root package.json script governance (orchestration-only, no feature alias uplift).
  • bun run ui:boundaries runs UI boundary checks (guards packages/core/src/tui/, packages/core/src/screens/, packages/core/src/components/ from importing forbidden layers).
  • bun run test runs vitest run; bun run test:watch runs Vitest watch.
  • Single test: bun run test -- packages/core/src/tools/registry.test.ts.
  • Package-specific commands (web/desktop/shared/semantics) live in each package AGENTS.md.

Read the full file on GitHub · 177 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.

  1. 3d ago First seen · 177 lines · 3,468 tokens per session scan A af0ab1e324d9

Subscribe to this mod's changes

formax AGENTS.md is an instructions file published in the GitHub repository yusifeng/formax (192 stars, last pushed 1mo ago), licensed MIT. It adds 3,468 tokens to every session, about $0.0173 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.

aiassistantclideveloper-toolsink
Related

Other instructions, from other repositories

qm AGENTS.md

AGENTS.md instructions for yc-software/qm, covering qm, working on the code, private forks and durable by default.

yc-software/qm · 1,797 tokens

dsh-TUI AGENTS.md

AGENTS.md instructions for ccch1mneyyy/dsh-TUI, covering agents.md, 仓库布局, 命令, 上游边界与契约 and 约定与红线.

ccch1mneyyy/dsh-TUI · 2,093 tokens

nullclaw CLAUDE.md

Instructions for nullclaw/nullclaw, covering claude.md, mandatory reference, build & test commands, requires exactly zig 0.16.0 (verify: zig version) and build flags.

nullclaw/nullclaw · 2,439 tokens

reverse-engineering-assistant CLAUDE.md

Instructions for cyberkaida/reverse-engineering-assistant, covering claude.md, project overview, build and test commands, java extension (ghidra plugin) and set ghidra installation directory first.

cyberkaida/reverse-engineering-assistant · 3,603 tokens

aghub AGENTS.md

Instructions for AkaraChen/aghub, covering aghub knowledge base, structure, where to look, conventions and rust.

AkaraChen/aghub · 1,294 tokens

openyida AGENTS.md

Instructions for openyida/openyida, covering openyida — ai agent 开发指引, 项目简介, 项目结构, skill 测评 harness（scripts/eval/） and 关键约定.

openyida/openyida · 5,810 tokens