jobseek: Agent for Claude Code

.claude/agents/jobseek-labeller-extract-role.md

jobseek-labeller-extract-role is an agent for Claude Code from colophon-group/jobseek. It costs 46 tokens per session (287 once invoked), scanned A, original, MIT.

A specialized agent that reads the role section of a job posting and extracts the role summary, responsibilities, collaborators, working hours, shifts, travel, and on-call details.

In plain words
What is it for?
Use it in the Jobseek labelling pipeline when a posting contains a role section.
Why use it?
It converts job-description text into consistent structured fields while preserving responsibility lists as written. Unstated details remain empty rather than being inferred.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is colophon-group/jobseek's own configuration. It tells Claude Code how to work on jobseek 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 jobseek configures →

Reuse

Borrowing it

Nothing to install: this file belongs to colophon-group/jobseek. 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/colophon-group/jobseek/main/.claude/agents/jobseek-labeller-extract-role.md
Clone the repo
git clone --depth 1 https://github.com/colophon-group/jobseek

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 jobseek-labeller-extract-role

README.md
[![agentmods](https://agentmods.dev/badge/agents/colophon-group/jobseek/jobseek-labeller-extract-role/github.svg)](https://agentmods.dev/agents/colophon-group/jobseek/jobseek-labeller-extract-role)
Your own site
<a href="https://agentmods.dev/agents/colophon-group/jobseek/jobseek-labeller-extract-role"><img src="https://agentmods.dev/badge/agents/colophon-group/jobseek/jobseek-labeller-extract-role/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 jobseek-labeller-extract-role

Your own site · 80×15
<a href="https://agentmods.dev/agents/colophon-group/jobseek/jobseek-labeller-extract-role"><img src="https://agentmods.dev/badge/agents/colophon-group/jobseek/jobseek-labeller-extract-role.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 287 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 $0.00046 $0.00287
Opus 5 $0.00023 $0.00143
Sonnet 5 $0.00009 $0.00057
Haiku 4.5 $0.00005 $0.00029

Measured 13d ago against content hash 0812575eabc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

jobseek-labeller-extract-role 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 13d 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/agents/jobseek-labeller-extract-role.md · 34 lines

What it actually says

You extract role-section fields for the jobseek labelling pipeline.

Invocation contract

User message has exactly two lines:

INPUT: <path>
OUTPUT: <path>
  1. Read the file at INPUT.
  2. Emit only what is evidenced.
  3. Write only valid JSON matching the schema to OUTPUT. First char {, last }, nothing else.
  4. Unrecoverable → {"error": "<reason>"}.

Hard rules

  • Use only Read and Write.
  • responsibilities are verbatim from the section (source language, no paraphrase, no sentence-splitting). Prefer the posting's bullet boundaries; if the section is a single paragraph, emit it as a single-element array.
  • role_summary is your 1–2 sentence English paraphrase; OK to reword.
  • Enum values must match exactly. null for unstated — do not guess hours, shift, or on-call status.

Retries

## Previous attempt failed → fix only those issues.

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. 13d ago First seen · 34 lines · 46 tokens per session scan A 0812575eabc7

Subscribe to this mod's changes

jobseek-labeller-extract-role is an agent published in the GitHub repository colophon-group/jobseek (191 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 287 once invoked, about $0.0002 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 2026-08-30.