What is jobseek-label-daily?

A command for running the daily Jobseek job-posting labelling process. It samples recent postings, sends them through specialized agents, checks the results, and uploads accepted records to Hugging Face.

Use it with optional date and sample-count settings to process a daily batch of postings and create accepted or rejected records in the labelled-postings dataset.

It coordinates the full workflow and enforces where intermediate and final files are stored. This avoids manually running each cleaning, extraction, validation, and upload step.

How colophon-group/jobseek configures Claude Code

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/commands/jobseek-label-daily.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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/colophon-group/jobseek/jobseek-label-daily/github.svg)](https://agentmods.dev/commands/colophon-group/jobseek/jobseek-label-daily)

Your own site

<a href="https://agentmods.dev/commands/colophon-group/jobseek/jobseek-label-daily"><img src="https://agentmods.dev/badge/commands/colophon-group/jobseek/jobseek-label-daily/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/colophon-group/jobseek/jobseek-label-daily"><img src="https://agentmods.dev/badge/commands/colophon-group/jobseek/jobseek-label-daily.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,749 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.02749
Opus 5	$0.00028	$0.01375
Sonnet 5	$0.00011	$0.00550
Haiku 4.5	$0.00006	$0.00275

Measured 13d ago against content hash f912214f0b59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

jobseek-label-daily scanned grade C with 2 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Never `rm -rf`. Rejected postings stay on disk (in the same `postings/`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Never invoke `gh`, `git`, `curl`, `mkdir`, `rm`, `mv`, `cat`,

.claude/commands/jobseek-label-daily.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the orchestrator for the daily labelled-postings routine. Follow this playbook verbatim. Do not improvise the pipeline, do not read or modify any subagent system prompts, do not make direct Anthropic API calls. Every LLM step is an Agent(...) invocation; every deterministic step is a labeller CLI call via Bash.

Arguments

Parse any arguments passed to the command:

--date YYYY-MM-DD (optional; default: today UTC)
--count N (optional; default: 24)

Bind these to RUN_DATE and SAMPLE_SIZE for the rest of the run.

Invariants

Read/Write files only under data/postings-labelled/ (relative to apps/crawler). The _runs/{RUN_DATE}/<id>/ subtree is where per-posting intermediates live; the final gold record is a single file at postings/{RUN_DATE}/<id>.json whose labelling_meta.qa_verdict is the status (accepted or rejected).
Never read any file under .claude/agents/ or apps/crawler/src/labeller/prompts/. Subagents load their own prompts.
Every Agent invocation uses subagent_type="jobseek-labeller-<task>" and model="sonnet". The prompt argument is exactly two lines:
```
INPUT: <path-to-rendered-input.md>
OUTPUT: <path-to-write-output.json>
```
Paths may contain spaces; the INPUT: / OUTPUT: prefixes are fixed.
After every Agent call, run labeller validate ... in Bash. If it fails, retry the subagent up to 2 times by re-rendering the task input with --previous-error "<validator output>" and re-invoking. If still failing after 2 retries, record the failure reason and move to the next posting (the posting will ultimately be merged with qa_verdict=rejected).

Step 0 — working directory

Run everything from apps/crawler:

cd apps/crawler

Step 1 — sample

labeller sample --date $RUN_DATE --count $SAMPLE_SIZE \
    --out data/postings-labelled/_runs/$RUN_DATE/sample.json

Read the sample file. It has a postings array with posting IDs. Let IDS be that list.

Read the full file on GitHub · 319 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.

13d ago First seen · 319 lines · 57 tokens per session scan C f912214f0b59

Subscribe to this mod's changes

jobseek-label-daily is a command published in the GitHub repository colophon-group/jobseek (191 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 2,749 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics Research ats careers greenhouse job-aggregator job-board job-posting

jobseek: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Recursive force deletehighDestructive command

Makes network callslowCapability

How it starts

Arguments

Invariants

Step 0 — working directory

Step 1 — sample

What this file has done since we first saw it

Other commands, from other repositories

setup

quick-eval

resume

resume-team

writing-coach

cover-letter