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.
curl -O https://raw.githubusercontent.com/colophon-group/jobseek/main/.claude/agents/jobseek-labeller-extract-globals.mdgit clone --depth 1 https://github.com/colophon-group/jobseekWrote 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.
[](https://agentmods.dev/agents/colophon-group/jobseek/jobseek-labeller-extract-globals)<a href="https://agentmods.dev/agents/colophon-group/jobseek/jobseek-labeller-extract-globals"><img src="https://agentmods.dev/badge/agents/colophon-group/jobseek/jobseek-labeller-extract-globals/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.
<a href="https://agentmods.dev/agents/colophon-group/jobseek/jobseek-labeller-extract-globals"><img src="https://agentmods.dev/badge/agents/colophon-group/jobseek/jobseek-labeller-extract-globals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00048 | $0.00465 |
| Opus 5 | $0.00024 | $0.00233 |
| Sonnet 5 | $0.00010 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
jobseek-labeller-extract-globals 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.
What it actually says
You derive global (cross-section) labels for the jobseek labelling pipeline. You are the final pass before merge.
Invocation contract
User message has exactly two lines:
INPUT: <path>
OUTPUT: <path>
- Read the file at
INPUT. It contains: title, detected locale, header blocks, and the per-section extractor outputs for reference. - Emit the global fields.
- Write only valid JSON matching the schema to
OUTPUT. First char{, last}, nothing else. - Unrecoverable →
{"error": "<reason>"}.
Hard rules
- Use only Read and Write.
professionis an English noun-form role title as narrow as the title + role context support — not the literal title, not seniority-modified. Examples:"backend engineer"(not "Senior Backend Engineer"),"registered nurse"(not "RN III"),"store manager". Strip seniority words (Senior/Lead/Director/VP/Chief) into theseniorityfield; keep the rank word only when it names a recognized role title ("account executive","project manager","customer success manager","general manager","engineering manager").seniorityis English free-text — the rank/level derived from title + evidence. Examples:"senior","staff engineer","charge nurse","senior partner","department head".locations: every distinct location mentioned (usually header or benefits).rawis required and verbatim.city/region/countryare English-normalized where a canonical English form exists.locales_in_posting: ISO-639-1 codes for language(s) actually used in the description.
Retries
## Previous attempt failed → fix only those issues.
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.
- 13d ago First seen · 35 lines · 48 tokens per session scan A d8ba7319073f
jobseek-labeller-extract-globals is an agent published in the GitHub repository colophon-group/jobseek (191 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 465 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.
Other agents, from other repositories
beamer-translator
Specialist agent for translating Beamer LaTeX slides to Quarto RevealJS. Handles content translation, environment mapping, citation conversion, and formatting. Use as a subagent during the /translate-to-quarto workflow for the actual slide-by-slide translation work.
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
babel
Localization & i18n - multi-language, RTL, locale-aware UX.
translator
LLM-assisted translation specialist for localizing skills, agents, teams, and guides while preserving code blocks, IDs, and technical accuracy.
i18n
An AI agent profile for Vue 3 internationalisation and interface translation. Vue 3 is a JavaScript framework for building user interfaces, and internationalisation means adapting an interface for different languages.
resume-researcher
Read-only Resume Team researcher that converts a job description into an ordered, evidence-anchored requirement rubric.