claude-works: Instructions file for Claude Code

CLAUDE.md

claude-works CLAUDE.md is an instructions file for Claude Code from andrewaws26/claude-works. It costs 1,195 tokens per session, scanned A, original, MIT.

The main instruction file for Claude Works, an MCP server for a job-application pipeline. It documents the system's honesty rules, setup, architecture, operating process, and lessons for handling application forms.

In plain words
What is it for?
Use it when maintaining Claude Works, onboarding candidates, driving ATS forms, reviewing application plans, or recording reusable lessons about job-submission workflows.
Why use it?
It gives maintainers one place to follow the project's rules and preserve fixes discovered during use. An ATS is an applicant-tracking system that companies use to collect and process applications.

Instructions file for Claude Code

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

This is andrewaws26/claude-works's own configuration. It tells Claude Code how to work on claude-works 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 claude-works configures →

Reuse

Borrowing it

Nothing to install: this file belongs to andrewaws26/claude-works. 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/andrewaws26/claude-works/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/andrewaws26/claude-works

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 claude-works CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/andrewaws26/claude-works/claude-md.svg)](https://agentmods.dev/instructions/andrewaws26/claude-works/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/andrewaws26/claude-works/claude-md"><img src="https://agentmods.dev/badge/instructions/andrewaws26/claude-works/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,195 This file is loaded in full into every session.
When invoked 1,195 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 $0.01195 $0.01195
Opus 5 $0.00598 $0.00598
Sonnet 5 $0.00239 $0.00239
Haiku 4.5 $0.00120 $0.00120

Measured 7d ago against content hash 335e403386e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-works 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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Claude Works is an MCP server (FastMCP, stdio) exposing a job-application pipeline as typed tools. The honesty policy lives in the modules, not in prompts: hard caps in scoring, gate findings in the resume tools, fill-and-park plans in submission. Do not move policy into docstrings or prompt text.

Companion docs, read before the matching work: PLAYBOOK.md (every per-ATS form-driving lesson; read it before executing a submission plan with Playwright), OPERATING.md (the loop's operating model: queue-first gate, hard walls, de-dup semantics, cadence). To onboard a new candidate end to end, run the bundled /setup command.

Standing rule: append lessons in the same session

When you discover a better way to fill or submit a form (a new ATS, a selector, a validator trick, a submit-blocker), append it to PLAYBOOK.md AND, in terse generic form, to submission.py's ATS_GOTCHAS (tests green, no PII, no em dashes) before the session ends. When a skip reveals a pattern, add it to curation.py's filters. This is how the system remembers; do not wait to be asked.

Commands

pip install -e ".[dev]"          # dev install
ruff check . && mypy && pytest   # the exact checks CI runs (no network needed)
python -m claude_works           # run the server over stdio

Demo mode (all 14 tools work offline, from this clone):

JOBSEARCH_DATA_DIR="$PWD/examples" \
JOBSEARCH_RESUMES_DIR="$PWD/examples/resumes" \
python -m claude_works

Setting it up for a user

Prefer the bundled /setup command: it interviews the user for example jobs + their resume and derives everything below from those examples. The manual outline:

  1. pip install claude-works (PyPI) or pip install -e . from a clone.
  2. Create a data directory for their search (ledger, queue, and policy live there; empty is fine, readers degrade gracefully).
  3. Copy examples/policy.sample.json to <data dir>/policy.json and edit it WITH them: their excluded companies, skill gaps, level terms, scoring vocabulary, curation lanes. The defaults are one specific candidate's policy; never let a new user run on them.
  4. Register the server (identity is env-only; nothing personal is in code):

Read the full file on GitHub · 102 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 · 102 lines · 1,195 tokens per session scan A 335e403386e4

Subscribe to this mod's changes

claude-works CLAUDE.md is an instructions file published in the GitHub repository andrewaws26/claude-works (0 stars, last pushed 2d ago), licensed MIT. It adds 1,195 tokens to every session, about $0.0060 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 2026-09-01.

Related

Other instructions, from other repositories

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 · 5,153 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

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

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

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