speclaw: Instructions file for Claude Code

CLAUDE.md

speclaw CLAUDE.md is an instructions file for Claude Code from esneiderbravo/speclaw. It costs 2,272 tokens per session, scanned A, original, MIT.

A set of instructions for Claude Code in the Speclaw repository, a project that helps turn code repositories into specification-driven projects.

In plain words
What is it for?
Use it when working in Speclaw to follow its lawbook, architecture, coding, testing, documentation, and contribution rules.
Why use it?
It tells the coding agent which rules and standards to read before changing code, reducing the risk of violating project requirements.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is esneiderbravo/speclaw's own configuration. It tells Claude Code how to work on speclaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything speclaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to esneiderbravo/speclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/esneiderbravo/speclaw/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/esneiderbravo/speclaw

Made for: Claude Code.

Wrote 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.

agentmods badge for speclaw CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/esneiderbravo/speclaw/claude-md.svg)](https://agentmods.dev/instructions/esneiderbravo/speclaw/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/esneiderbravo/speclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/esneiderbravo/speclaw/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,272 This file is loaded in full into every session.
When invoked 2,272 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02272 $0.02272
Opus 5 $0.01136 $0.01136
Sonnet 5 $0.00454 $0.00454
Haiku 4.5 $0.00227 $0.00227

Measured 7d ago against content hash 89622ce82395, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

speclaw 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 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.

CLAUDE.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — speclaw Agent Operating Rules

Agent rules for the speclaw repository (a self-contained MCP suite + CLI that turns any repo into a spec-driven, agent-ready project — Foundation, Compass, Lawbook; 100% local). These rules are STRICT. Read this file at the start of every session. Cross-agent context: AGENTS.md · The law: LAWS.md


Rule 0 — The Law comes first

Read LAWS.md before writing or changing any code. It is the constitution: it binds the individual standards below. Open the standard that governs the area you're touching before touching it:

You're working on… Read first
Anything docs/standards/base-standards.md
Structure / boundaries docs/standards/architecture.md
Backend code docs/standards/backend-standards.md
Frontend code docs/standards/frontend-standards.md
Tests / gates docs/standards/testing-standards.md
Docstrings / API comments docs/standards/documentation.md
Branches / PRs / tickets docs/standards/conventions.md
Any non-trivial change docs/standards/lawbook.md

When any instruction conflicts with a standard, the standard wins — and if you believe it is wrong, propose an amendment via a spec change; never silently ignore it.

Rule 1 — Compass first, always

This repo is indexed by Compass, speclaw's local code graph (.speclaw/). For any question about code — what a symbol is, what it uses, who calls it, where it lives, how a value flows — call Compass first: compass_find / compass_explore to locate and read a symbol with its callers and callees, compass_impact (grouped by module; format: flat for the old list) / compass_trace for blast radius and call paths, compass_affected_tests / speclaw affected-tests --from-diff for which tests to run, compass_hotspots / speclaw hotspots (activity × AST health, default 90d) and compass_coupling / speclaw coupling (Jaccard strength, in_graph, isTestPair). Run compass_index first if the graph is missing. Schema 10 stores FTS5/node_text/pagerank plus embedding_cache, Merkle dir_hashes, and node_metrics — reindex with speclaw index after a schema bump (9→10 migrates; 8→9 preserves embeddings).

Read the full file on GitHub · 149 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. 7d ago First seen · 149 lines · 2,272 tokens per session scan A 89622ce82395

Subscribe to this mod's changes

speclaw CLAUDE.md is an instructions file published in the GitHub repository esneiderbravo/speclaw (1 stars, last pushed 4d ago), licensed MIT. It adds 2,272 tokens to every session, about $0.0114 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.

Related

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens