Borrowing it
Nothing to install: this file belongs to mhawthorne/gza. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mhawthorne/gza/main/AGENTS.mdgit clone --depth 1 https://github.com/mhawthorne/gzaWrote 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/mhawthorne/gza/agents-md)<a href="https://agentmods.dev/instructions/mhawthorne/gza/agents-md"><img src="https://agentmods.dev/badge/instructions/mhawthorne/gza/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/mhawthorne/gza/agents-md"><img src="https://agentmods.dev/badge/instructions/mhawthorne/gza/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02943 | $0.02943 |
| Opus 5.5 | $0.01177 | $0.01177 |
| Sonnet 5.5 | $0.00589 | $0.00589 |
| Haiku 4.5 | $0.00294 | $0.00294 |
Grade A, and why
gza 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gza
A coding AI agent runner for Claude Code.
Keep AGENTS.md under 100 lines. Move details to docs/. This file is for critical agent behavioral rules only.
Essential Commands
Always use uv run gza (not gza directly or python -m gza).
gza add "prompt" # Add a task (default type: implement)
gza work [-b] # Run next pending task (-b for background)
gza next # List pending tasks
gza history # List recent completed/failed tasks
gza advance # Progress unmerged tasks through lifecycle
gza lineage <id> # Show task's ancestor/descendant tree
gza migrate [--status] # Run manual DB migrations (e.g. v25/v26 task-ID migrations)
See docs/ for detailed documentation:
- docs/configuration.md — full command list, all options, config reference
- docs/skills.md — skill usage and authoring
- docs/docker.md — Docker setup, custom Dockerfiles, provider auth
- docs/merge-policy.md — review severity and merge-gate policy (
BLOCKERblocks merge;FOLLOWUPships with follow-up) - docs/internal/ — internal architecture, design notes & practices (index); writing/maintaining docs: writing-docs.md
Critical Rules
Getting code merged is the top priority. A stuck task should be pushed toward a real merge, not left to accumulate more review/improve cycles. Prefer a bounded, auditable override (e.g. force-approving a stale/inconclusive review) over re-running a review that risks re-parking the task on a new nitpick.
Task management: When the user mentions "task", "add a task", or asks to track something for later, use uv run gza add "...". NEVER edit etc/todo.txt or other files manually.
Default to filing a gza task: When the user asks for a substantive code change (a feature, fix, or refactor), file it with uv run gza add rather than editing inline — do NOT start editing right away. Work in-line only when the user explicitly says to, or for trivial edits. If unsure which way they want it, ask before implementing.
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.
- 1mo ago Changed · +80 lines · +957 tokens per session 02a227c98dd6
- 1mo ago Changed · +1 lines · +152 tokens per session 50a9baa725e9
- 1mo ago First seen · 100 lines · 1,834 tokens per session scan A d46b82d4f642
gza AGENTS.md is an instructions file published in the GitHub repository mhawthorne/gza (12 stars, last pushed 6d ago), licensed MIT. It adds 2,943 tokens to every session, about $0.0118 per session on Opus 5.5. 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
vscode buildNext.instructions.md
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
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, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.