Borrowing it
Nothing to install: this file belongs to PenguinAlleyApps/agents-of-the-alley. 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/PenguinAlleyApps/agents-of-the-alley/main/CLAUDE.mdgit clone --depth 1 https://github.com/PenguinAlleyApps/agents-of-the-alleyWrote 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/penguinalleyapps/agents-of-the-alley/claude-md)<a href="https://agentmods.dev/instructions/penguinalleyapps/agents-of-the-alley/claude-md"><img src="https://agentmods.dev/badge/instructions/penguinalleyapps/agents-of-the-alley/claude-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/penguinalleyapps/agents-of-the-alley/claude-md"><img src="https://agentmods.dev/badge/instructions/penguinalleyapps/agents-of-the-alley/claude-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 | $0.00891 | $0.00891 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
agents-of-the-alley CLAUDE.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 12d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{Your Project Name} — Agents of the Alley
Replace this with your project identity. What are you building? Who is the user? What's the non-negotiable north star?
Architecture
This project follows the 4-layer context engineering pattern from Agents of the Alley.
| Layer | What | Source |
|---|---|---|
| 1 Identity | This file + agents/*.md + playbooks |
Git-tracked, read-only to agents |
| 2 State | state/ + per-product STATE files |
Rewritten per session |
| 3 Relevant | RAG search (pgvector / SQLite / custom) | Fetched on demand |
| 4 Archive | Everything else in git history | Grep-searchable, never auto-loaded |
Agents
Edit agents/*.md to suit your project. Each agent has:
- Identity (department, model, activation)
- Context Loading (what files they always read)
- Output (what they produce)
- Refinement Questions (5-10 domain questions, each with evidence requirement)
- Knowledge Graph (bidirectional links — EO-006 compliance)
Sample agents included:
| Agent | Role |
|---|---|
| Planner | Scopes work, writes REFINED_SPEC, decides kill signals |
| Builder | Implements from spec, runs spec-compliance check before commit |
| Reviewer | Audits spec vs reality, gatekeeper on phase transitions |
| Researcher | Web search + RAG lookup, produces evidence-backed answers |
| Deployer | Ships to production with security + observability gates |
Non-negotiable rules
- Files ≤ 150 lines. Beyond → split into focused sub-files or archive to RAG.
- Agent files ≤ 55 lines. Compress before adding.
- No tiers. Full workflow for every non-trivial task.
- Cross-reference or it didn't happen. Every new insight → canonical file + RAG ingest + bidirectional link.
- Refinement Questions require evidence. No "I think" — cite URL, number, or explicit "no data found".
- Zero gaps before commit. Agents self-verify against the original spec, point by point, before saying "done".
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.
- 12d ago First seen · 72 lines · 891 tokens per session scan A e74e0e12d169
agents-of-the-alley CLAUDE.md is an instructions file published in the GitHub repository PenguinAlleyApps/agents-of-the-alley (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 891 tokens to every session, about $0.0045 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 2026-08-31.
Other instructions, from other repositories
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.
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.
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).
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).