witness-mcp: Skill for Claude Code

.claude/skills/apply-to-job/SKILL.md

apply-to-job is a skill for Claude Code from Zetetic-Dhruv/witness-mcp. It costs 58 tokens per session (371 once invoked), scanned A, original, Apache-2.0.

A job-application helper that reads a job-posting URL and fills the employer's application fields from the user's profile. It also prepares supporting material and leaves final submission to the user.

In plain words
What is it for?
Use it to prepare applications from Greenhouse, Ashby, and other job forms, review missing information, and assemble tailored application content.
Why use it?
It removes repetitive form filling while avoiding guesses about required answers, salary, relocation, or other personal details.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/skills/apply-to-job/SKILL.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 apply-to-job

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/zetetic-dhruv/witness-mcp/apply-to-job"><img src="https://agentmods.dev/badge/skills/zetetic-dhruv/witness-mcp/apply-to-job.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 371 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00058 $0.00371
Opus 5 $0.00029 $0.00186
Sonnet 5 $0.00012 $0.00074
Haiku 4.5 $0.00006 $0.00037

Measured 11d ago against content hash 804ac12b3b29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

apply-to-job 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/skills/apply-to-job/SKILL.md · 22 lines

What it actually says

apply-to-job

Steps

  1. Run: python -m src.cli --data-dir <folder> apply --url "<JOB_URL>" --company "<Name>"
    • Greenhouse + Ashby return the company's exact fields (incl. custom questions); others return a complete standard set. Output → <folder>/applications/<company>.json.
    • If the result has fetch_failed: true, the real form couldn't load — tell the user, and have them verify the actual questions on the apply page. Do NOT present generic fields as the real form.
  2. Read the JSON and present it as a clean field → value list. Then:
    • Fill needs_input (required) and review (e.g. salary, notice, relocation) with the user — never guess.
    • The nontrivial block holds a reframe, a product teardown, a proof-map, and honest risks. Use its why_us for the motivation field; tailor further with make-nontrivial / tailor-answer.
  3. Give them the apply_url and remind them: nothing is auto-submitted — they review and click submit.
  4. Log it in <folder>/memory/job-hunt-status.md.

Truthful to <folder>/profile.json only. With ANTHROPIC_API_KEY set, add --llm to auto-draft open answers.

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 · 22 lines · 58 tokens per session scan A 804ac12b3b29

Subscribe to this mod's changes

apply-to-job is a skill published in the GitHub repository Zetetic-Dhruv/witness-mcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 371 once invoked, about $0.0003 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 skills, from other repositories