agentmods.dev

liam AGENTS.md

A repository guide for the Liam codebase, describing its folders, development commands, coding style, and testing rules.

In plain words
What is it for?
Use it when adding or changing Liam apps, shared packages, internal tools, or documentation, and when running builds, formatting, linting, or tests.
Why use it?
It gives a coding agent the project-specific information needed to make changes that fit the repository and use the right checks.

Instructions file for CodexOpenCode

5.1k 3d ago A scan 657 tokens original Apache-2.0
View the source file liam-hq/liam
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/liam-hq/liam/agents-md
Clone the repo
git clone --depth 1 https://github.com/liam-hq/liam

Made for: Codex, OpenCode.

Per session 657 This file is loaded in full into every session.
When invoked 657 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 $0.00657 $0.00657
Opus 5 $0.00329 $0.00329
Sonnet 5 $0.00131 $0.00131
Haiku 4.5 $0.00066 $0.00066

Measured yesterday against content hash efb4b624a887, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

liam 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 yesterday.

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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Modules

  • frontend/apps/*: Next.js apps (e.g., @liam-hq/app, @liam-hq/docs).
  • frontend/packages/*: Shared libraries and tools (e.g., schema, erd-core, cli, ui).
  • frontend/internal-packages/*: Infra and tooling (e2e, configs, storybook, agent).
  • assets/: Images and media. docs/: Documentation. scripts/: Repo utilities.

Build, Test, and Development

  • Install: pnpm install
  • All apps/packages (Turbo):
    • Dev: pnpm dev (or one app: pnpm -F @liam-hq/app dev)
    • Build: pnpm build
    • Test (unit): pnpm test
    • E2E (Playwright): pnpm test:e2e
    • Coverage: pnpm test:coverage
  • App-only examples:
    • Run Next dev: pnpm -F @liam-hq/app dev:next
    • Build Next: pnpm -F @liam-hq/app build

Coding Style & Naming

  • Language: TypeScript/TSX; React components in PascalCase (e.g., App.tsx); utilities in camelCase (e.g., mergeSchema.ts).
  • CSS Modules: *.module.css with typed CSS via typed-css-modules.
  • Lint/Format: Biome and ESLint. Run pnpm fmt and pnpm lint. Pre-commit hooks run pnpm lint (see lefthook.yml).

Testing Guidelines

  • Unit tests: Vitest. Place near source as *.test.ts(x) or in __tests__/.
  • E2E tests: Playwright in frontend/internal-packages/e2e.
  • Commands: pnpm test for unit, pnpm test:e2e for Playwright, pnpm test:coverage for V8 coverage.

Commit & Pull Requests

  • Commit style: Conventional Commits (e.g., feat:, fix:, chore(deps): ...).
  • Before pushing: pnpm fmt && pnpm lint && pnpm test.
  • PRs: clear description, linked issues, screenshots for UI changes, and note any env or migration impacts.
  • Versioning: If you change a publishable package, add a changeset: pnpm changeset.

Security & Configuration

  • Environment: use .env/.env.local (created automatically by pnpm prebuild). Never commit secrets.
  • Sync Vercel envs (optional): pnpm vercel:env-pull and link with pnpm vercel:link.
  • Common vars: NEXT_PUBLIC_*, Sentry keys, and job runner tokens (see turbo.json env list).

Read the full file on GitHub · 45 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. yesterday First seen · 45 lines · 657 tokens per session scan A efb4b624a887

Subscribe to this mod's changes

liam AGENTS.md is an instructions file published in the GitHub repository liam-hq/liam (5,100 stars, last pushed 3d ago), licensed Apache-2.0. It adds 657 tokens to every session, about $0.0033 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.

DatabasesTestingWriting and docsdata-visualizationdatabase-schemadocumentationdocumentation-toolentity-relationship-diagram
Related

Other instructions, from other repositories

laravel-truss CLAUDE.md

Instructions for albertoarena/laravel-truss, covering claude.md — instructions for claude code, project overview, stack, commands and conventions (always true).

albertoarena/laravel-truss · 1,469 tokens

ovellum CLAUDE.md

Claude Code instructions for oinam/ovellum, covering claude, your role, how this repo is laid out, commands and working agreements.

oinam/ovellum · 938 tokens

docshark copilot-instructions.md

Instructions for Michael-Obele/docshark, covering docshark site — copilot instructions, tech stack & architecture, essential commands, coding conventions and quality gate.

Michael-Obele/docshark · 2,719 tokens

SchemaCrawler-AI AGENTS.md

AGENTS.md instructions for schemacrawler/SchemaCrawler-AI, covering agents.md — schemacrawler-ai, build and test, standard build and unit tests (java 21 required), with docker-based image verification (requires docker) and module layout.

schemacrawler/SchemaCrawler-AI · 963 tokens

SchemaCrawler-AI copilot-instructions.md

Copilot instructions for schemacrawler/SchemaCrawler-AI, covering instructions for java projects using apache maven, general coding guidelines, project structure, dependencies and versions and testing and quality.

schemacrawler/SchemaCrawler-AI · 294 tokens

typo3-docs-skill AGENTS.md

AGENTS.md instructions for netresearch/typo3-docs-skill, covering agents.md — typo3 documentation skill, repo structure, commands, rules and references.

netresearch/typo3-docs-skill · 928 tokens