What is claude-auto-context CLAUDE.md?

Repository instructions for Claude Code work on the claude-auto-context project. They describe how version files, offers, background workers, database paths, hooks, and crash recovery must be handled.

Use them when changing the plugin, its offer detection, worker startup and recovery, hooks, version scripts, or related documentation.

They prevent changes from using mismatched versions, the wrong database, or unsafe worker recovery rules. They also document details that are easy to miss when maintaining the project.

How getklaim/claude-auto-context configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to getklaim/claude-auto-context. 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/getklaim/claude-auto-context/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/getklaim/claude-auto-context

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/getklaim/claude-auto-context/claude-md.svg)](https://agentmods.dev/instructions/getklaim/claude-auto-context/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/getklaim/claude-auto-context/claude-md"><img src="https://agentmods.dev/badge/instructions/getklaim/claude-auto-context/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 546 This file is loaded in full into every session.

When invoked 546 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00546	$0.00546
Opus 5	$0.00273	$0.00273
Sonnet 5	$0.00109	$0.00109
Haiku 4.5	$0.00055	$0.00055

Measured 6d ago against content hash 8ee7b8e661e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-auto-context 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 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.

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 · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Version Sync

Version must match in 3 files: .claude-plugin/plugin.json, .claude-plugin/marketplace.json, package.json
scripts/bump-version.sh syncs all 3 on commit via PreToolUse hook (not git pre-commit hook)

Offers System

Detection: scripts/on-user-prompt-submit.sh greps ^applied$ (bare word, not ## Status: applied)
Offer format: ## Status\npending / ## Status\napplied

Worker Runtime

Canonical DB: .claude-auto-context/db/claude-auto-context.db (NOT auto-context.db)
Hooks config: hooks/hooks.json; logs: .claude-auto-context/db/worker.log
STALE_THRESHOLD_S must exceed AGENT_TIMEOUT_MS / 1000 (currently 650s > 600s) — if smaller, self-heal loop prematurely recovers still-active events, causing duplicate processing
On startup, selfHeal(db, true) (forceAll=true) must run before the poll loop to recover events left in processing state by a previously crashed/SIGKILL'd worker
SIGKILL cannot be caught; stale lock file is handled by scripts/worker-launcher.sh via kill -0 on the stored PID — stale lock is removed before relaunch
worker.mjs uses Bun-specific built-ins (bun:sqlite); syntax is verified by bun --check via PostToolUse hook (bun-check-after-mjs-edit.sh) — do NOT call bun --check manually via Bash tool (hook runs in ~50ms; Bash tool adds ~2min approval overhead)

Rules Files

Frontmatter key is paths: (NOT globs:) — using an unrecognized key like globs: causes the rule to load unconditionally for ALL files

External Documentation

Claude Code docs: https://code.claude.com/docs/en/ (NOT docs.anthropic.com)

Skills Distribution

Plugin skills live in skills/ (plugin root) — auto-discovered when plugin is enabled
.claude/skills/ is the user's project-local directory, not used by this plugin

Subprocess Spawning

CLAUDECODE env var must be unset before spawning claude -p or Agent SDK (double-fix: shell launcher + process.env delete)
claude -p hangs indefinitely inside Claude Code sessions — must run from standalone terminal

Read the full file on GitHub · 30 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.

6d ago First seen · 30 lines · 546 tokens per session scan A 8ee7b8e661e0

Subscribe to this mod's changes

claude-auto-context CLAUDE.md is an instructions file published in the GitHub repository getklaim/claude-auto-context (10 stars, last pushed 5mo ago), licensed MIT. It adds 546 tokens to every session, about $0.0027 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.

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

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

claude-auto-context: Instructions file for Claude Code