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/etr/groundwork/agents-mdgit clone --depth 1 https://github.com/etr/groundworkWhat 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 | $0.01948 | $0.01948 |
| Opus 5 | $0.00974 | $0.00974 |
| Sonnet 5 | $0.00390 | $0.00390 |
| Haiku 4.5 | $0.00195 | $0.00195 |
Grade A, and why
groundwork 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- groundwork CLAUDE.md — 97% identical, 8 lines differ
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
Project Overview
Groundwork is a Claude Code plugin that provides a skills library for structured development workflows. It contains 40 skills spanning the full lifecycle — discovery, domain modeling, architecture, planning, TDD, debugging, validation, and shipping. Every capability is a skill; there is no separate commands layer (skills are both user-invocable via /groundwork:<name> and, where appropriate, model-invocable).
The using-groundwork skill is the lifecycle router: it maps work → skill across every phase and is the only way the model can surface user-only leaves (which are invisible to it at call time). When authoring or editing a skill, see docs/developing-skills.md (contributor guide: anatomy, frontmatter, tier selection, authoring discipline, progressive disclosure).
Project Structure
This is a Claude Code plugin, not a traditional software project. There is no build step for Claude Code use. A separate installer (install-skills.sh) exports the skills to other AI coding harnesses (see "Multi-target installation" below).
groundwork/
├── .claude-plugin/plugin.json # Plugin manifest
├── skills/ # Markdown-based workflow skills (SKILL.md files) — the only entry-point layer
├── agents/ # Subagent definitions (AGENT.md files)
├── hooks/ # Event-driven automation (SessionStart, PostToolUse, SubagentStop, PreCompact)
├── lib/ # JavaScript utilities (+ co-located *.test.js)
├── references/ # Runtime reference files loaded by skills/agents
│ ├── checklists/ # Shared checklists read by BOTH a producer skill and a reviewer agent (testing: test-driven-development ↔ test-quality-reviewer; accessibility: ux-design ↔ design-consistency-checker)
│ └── engineering-principles.md # Named-principle vocabulary (deep modules, Hyrum's Law, Chesterton's Fence, …)
├── tests/ # Node test suites; run via tests/run-tests.sh
├── docs/ # User-facing documentation
├── install-skills.sh # Multi-target export installer (Codex, OpenCode, Kiro, Pi)
├── install-config.txt # Export exceptions (drops + renames); fail-closed by default
└── pi-extension/ # Pre-built TypeScript extension copied into Pi installs
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.
- yesterday First seen · 134 lines · 1,948 tokens per session scan A 0dfeae0e6714
groundwork AGENTS.md is an instructions file published in the GitHub repository etr/groundwork (42 stars, last pushed 20d ago), licensed MIT. It adds 1,948 tokens to every session, about $0.0097 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.