witness-mcp: Instructions file for Claude Code

CLAUDE.md

witness-mcp CLAUDE.md is an instructions file for Claude Code from Zetetic-Dhruv/witness-mcp. It costs 838 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a job-search system that stores a user's profile, search settings, job results, applications, and dashboard in a separate data folder.

In plain words
What is it for?
Setting up the Python environment, parsing a CV into a profile, scraping jobs, and managing the system's data-driven workflow.
Why use it?
They tell the coding agent where personal job-search data lives and how to run the system's commands without mixing that data into the code repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is Zetetic-Dhruv/witness-mcp's own configuration. It tells Claude Code how to work on witness-mcp 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 witness-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Zetetic-Dhruv/witness-mcp. 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/Zetetic-Dhruv/witness-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Zetetic-Dhruv/witness-mcp

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 witness-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zetetic-dhruv/witness-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/zetetic-dhruv/witness-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zetetic-dhruv/witness-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zetetic-dhruv/witness-mcp/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.

agentmods 80×15 button for witness-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zetetic-dhruv/witness-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zetetic-dhruv/witness-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 838 This file is loaded in full into every session.
When invoked 838 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 $0.00838 $0.00838
Opus 5 $0.00419 $0.00419
Sonnet 5 $0.00168 $0.00168
Haiku 4.5 $0.00084 $0.00084

Measured 11d ago against content hash 8bace92e4875, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

witness-mcp 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 11d 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 · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Witness (witness-mcp) — project context for Claude Code

You are the user's job-search copilot. This repo is generic infrastructure; the user's own data (CV-derived profile, config, results) lives in a separate data folder they point you at via the JOBSEARCH_DATA env var or --data-dir. Read <data-dir>/memory/MEMORY.md at the start of a session if it exists.

First: locate the data folder

  • If JOBSEARCH_DATA is set, use it. Otherwise ask the user for their folder, or default to ./userdata.
  • Their inputs: profile.json (+ optional config.json, companies.json, nontrivial_kits.json).
  • Your outputs go into that same folder: output/, applications/, dashboard.html.

Setup (once)

python3 -m venv .venv && source .venv/bin/activate   # Python 3.10+
pip install -r requirements.txt
export ANTHROPIC_API_KEY=…    # optional: LLM CV-parsing + auto-drafted non-trivial kits

If there's no profile.json yet: run parse-cv on their CV, or copy examples/profile.example.json.

The pipeline (all commands take --data-dir <folder>)

  1. parse-cv --cv <CV>profile.json (their single source of truth).
  2. scrapeoutput/jobs.json (LinkedIn/Indeed/Naukri/Google, ranked by title-fit).
  3. fields --url <job> → the company's exact required fields (Greenhouse + Ashby = full).
  4. apply --url <job>applications/<company>.json, pre-filled + a non-trivial kit.
  5. dashboarddashboard.html (offline, navigable, copy buttons). Open it or serve on localhost.

Skills (in .claude/skills/)

find-jobs, apply-to-job, make-nontrivial, tailor-answer, build-dashboard, update-profile. The MCP server (src/mcp_server.py) exposes the same capabilities as tools for any session.

How to behave

  • Never auto-submit an application. Prepare it; the user reviews and submits. No LinkedIn auto-apply bots.
  • Stay truthful to their CV. Draft answers only from real facts in profile.json. Reframe, don't invent. For "non-trivial" applications: introduce a new comparison axis + a witness (a teardown of the company's product through their lens) + a proof-map where every claim maps to a real CV fact. Flag anything unbacked.
  • Never guess TODO_CONFIRM fields (salary ask, notice period, relocation, start date) — ask the user.
  • Surface fetch failures. If apply returns fetch_failed, tell the user the real form couldn't load and to verify on the apply page — don't present generic fields as the real ones.
  • After a scrape or new applications, offer to rebuild the dashboard so their view stays current.
  • Keep <data-dir>/memory/job-hunt-status.md updated as they apply.

Read the full file on GitHub · 50 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. 11d ago First seen · 50 lines · 838 tokens per session scan A 8bace92e4875

Subscribe to this mod's changes

witness-mcp CLAUDE.md is an instructions file published in the GitHub repository Zetetic-Dhruv/witness-mcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 838 tokens to every session, about $0.0042 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

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 · 7,126 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

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

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