Borrowing it
Nothing to install: this file belongs to andrewstellman/quality-playbook. 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/andrewstellman/quality-playbook/main/AGENTS.mdgit clone --depth 1 https://github.com/andrewstellman/quality-playbookWrote 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/andrewstellman/quality-playbook/agents-md)<a href="https://agentmods.dev/instructions/andrewstellman/quality-playbook/agents-md"><img src="https://agentmods.dev/badge/instructions/andrewstellman/quality-playbook/agents-md.svg" alt="Measured on agentmods" 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 | $0.09416 | $0.09416 |
| Opus 5 | $0.04708 | $0.04708 |
| Sonnet 5 | $0.01883 | $0.01883 |
| Haiku 4.5 | $0.00942 | $0.00942 |
Grade A, and why
quality-playbook 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 7d 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Playbook — Agent Guide
This file helps AI coding agents work on this repository. Read it first.
Rehydrate on context loss (ERR — read this first if you were summarized)
If your context was summarized, truncated, compacted, or continued from a prior session — i.e. you are reasoning from a summary rather than the original material (you will usually see a system note that the conversation was continued) — then before taking any action:
- Recognize that your working context is now a lossy re-rendering. Summaries drift toward restating decisions and your own prior output, and away from the user's literal intent.
- Rehydrate from the source of truth: for the release in flight, the
canonical
docs/design/QPB_v<X.Y.Z>_Design.md+_Implementation_Plan.md;ai_context/DEVELOPMENT_PROCESS.md(how QPB is built); andSKILL.md(what the skill must do). Read those as ground truth; treat the summary, your earlier notes, and derived docs (IMPROVEMENT_LOOP.md, work-item lists, changelogs, prior instructions, this guide's prose) as suspect — they are summaries, not specifications. - Re-ground the task against the literal text of the canonical doc — cite the design-doc section / FR and check your action matches the words, not your memory of them.
- If the source of truth and a derived artifact (or your own prior plan) conflict, stop and surface the conflict rather than proceeding on the drifted version.
Do this on every context-loss event, not only when something feels wrong — drift is silent. (Externalize–Recognize–Rehydrate: the spec lives on disk; recognize the context-loss event; rehydrate from durable truth instead of the lossy summary.)
What this repo is
The Quality Playbook is a skill for AI coding agents that explores any codebase from scratch and finds real bugs. It generates nine quality artifacts including a consolidated bug report with regression test patches, fix patches, and TDD red/green verification. It works with any language (Python, Java, Go, Rust, TypeScript, C, etc.) and any AI coding agent (Claude Code, GitHub Copilot, Cursor). v1.5.3 adds a skill-as-code surface (project-type classifier; four-pass generate-then-verify pipeline; skill-divergence taxonomy with internal-prose / prose-to-code / execution categories; skill-project gate enforcement) so the same divergence model that finds defects in code can find defects in AI skills — see previous_runs/v1.5.3/ for the bootstrap evidence.
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.
- 7d ago First seen · 319 lines · 9,416 tokens per session scan A 605f662660b1
quality-playbook AGENTS.md is an instructions file published in the GitHub repository andrewstellman/quality-playbook (84 stars, last pushed 3d ago), licensed Apache-2.0. It adds 9,416 tokens to every session, about $0.0471 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.
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.
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 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
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.