extract-rules

extract-rules is a skill for Claude Code from getklaim/claude-auto-context. It costs 31 tokens per session (1,187 once invoked), scanned B, original, MIT.

A session-review tool that finds project conventions and hard-to-guess lessons, then saves them as local rules for future work.

In plain words
What is it for?
Use it to turn corrections, unusual commands, safety restrictions, ordering requirements, and project-specific patterns from past sessions into reusable rules.
Why use it?
It prevents the coding agent from repeating mistakes or overlooking team practices that are not visible in the code or configuration.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the claude-auto-context plugin — 6 skills, 2 agents, 6 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/getklaim/claude-auto-context/extract-rules
Any agent
npx skills add getklaim/claude-auto-context --skill extract-rules
Clone the repo
git clone --depth 1 https://github.com/getklaim/claude-auto-context

Made for: Claude Code.

Or install claude-auto-context, the plugin that ships this one along with the rest of its 6 skills, 2 agents, 6 hooks.

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 extract-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/getklaim/claude-auto-context/extract-rules.svg)](https://agentmods.dev/skills/getklaim/claude-auto-context/extract-rules)
Your own site
<a href="https://agentmods.dev/skills/getklaim/claude-auto-context/extract-rules"><img src="https://agentmods.dev/badge/skills/getklaim/claude-auto-context/extract-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00031 $0.01187
Opus 5 $0.00015 $0.00593
Sonnet 5 $0.00006 $0.00237
Haiku 4.5 $0.00003 $0.00119

Measured 6d ago against content hash 60db2e1b46e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

extract-rules scanned grade B with 1 finding 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Analyze session data to find implicit conventions, then create glob-scoped rules in `.claude/rules/local/`.
skills/extract-rules/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extract Rules

Analyze session data to find implicit conventions, then create glob-scoped rules in .claude/rules/local/.

Rules = "institutional memory" (Boris Cherny). When Claude makes a mistake, the correction becomes a permanent rule so it never repeats.

The Boris Test

For every candidate rule, ask: "Would removing this cause Claude to make mistakes?" If no → don't create it. If yes → create it.

What Belongs in Rules (extract these)

Rules capture what Claude CANNOT discover by reading code, configs, or package.json:

Category Example Why it's a rule
Past mistake prevention "Never use enum, always literal unions" Correction from user, not in any config
Non-obvious commands "Run bun run test:file -- 'glob'" Can't guess the flag syntax
Prohibitions "Never touch prod DB directly" Safety rail, not in code
Hidden sequencing "Refresh auth token before API calls" Order dependency not obvious from code
Convention divergence "Error handling: Result type, not try-catch" Project chose non-default pattern
Gotchas "File X re-exports from Y — edit Y, not X" Non-obvious indirection

What Does NOT Belong (never create these)

Bad Rule Why What to do instead
"This project uses TypeScript" tsconfig.json exists Nothing — Claude reads it
"Tests are in tests/" Discoverable from directory structure Nothing
"Use ES modules" package.json type:module Nothing
"Write clean code" Self-evident, every project wants this Nothing
"The API returns JSON" Discoverable from reading route handlers Nothing
Code style already enforced by linter ESLint/Prettier handles it deterministically Hook, not rule
Anything in CLAUDE.md already Duplication wastes tokens Reference CLAUDE.md
Frequently changing information Goes stale, causes wrong behavior Keep in code comments

Key principle (Anthropic official): "Never send an LLM to do a linter's job." If something can be enforced deterministically (format, lint, type-check), it should be a hook, not a rule.

Read the full file on GitHub · 104 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. 6d ago First seen · 104 lines · 31 tokens per session scan B 60db2e1b46e1

Subscribe to this mod's changes

extract-rules is a skill published in the GitHub repository getklaim/claude-auto-context (10 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,187 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens