llm-job-pipeline: Command for Claude Code

.claude/commands/jobs-add.md

jobs-add is a command for Claude Code from ncalavera/llm-job-pipeline. It costs 52 tokens per session (5,202 once invoked), scanned A, original, MIT.

A command for adding job sources to a vacancy pipeline. A source can be a company, a job board, or one specific job opening.

In plain words
What is it for?
Adding a company by name or careers URL, enabling a built-in board, or entering one job manually.
Why use it?
It avoids separate setup processes for different source types and sends added vacancies into the normal scoring workflow.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is ncalavera/llm-job-pipeline's own configuration. It tells Claude Code how to work on llm-job-pipeline 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 llm-job-pipeline configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/sources.py enable-board <id> # once per board id.

Reuse

Borrowing it

Nothing to install: this file belongs to ncalavera/llm-job-pipeline. 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/ncalavera/llm-job-pipeline/main/.claude/commands/jobs-add.md
Clone the repo
git clone --depth 1 https://github.com/ncalavera/llm-job-pipeline

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 jobs-add

README.md
[![agentmods](https://agentmods.dev/badge/commands/ncalavera/llm-job-pipeline/jobs-add/github.svg)](https://agentmods.dev/commands/ncalavera/llm-job-pipeline/jobs-add)
Your own site
<a href="https://agentmods.dev/commands/ncalavera/llm-job-pipeline/jobs-add"><img src="https://agentmods.dev/badge/commands/ncalavera/llm-job-pipeline/jobs-add/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 jobs-add

Your own site · 80×15
<a href="https://agentmods.dev/commands/ncalavera/llm-job-pipeline/jobs-add"><img src="https://agentmods.dev/badge/commands/ncalavera/llm-job-pipeline/jobs-add.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,202 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00052 $0.05202
Opus 5 $0.00026 $0.02601
Sonnet 5 $0.00010 $0.01040
Haiku 4.5 $0.00005 $0.00520

Measured 12d ago against content hash 476aafb47200, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

jobs-add scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

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

curl -s -L --max-time 10 "{CAREERS_URL}" | head -200
.claude/commands/jobs-add.md · 533 lines

How it starts

The opening of the file, as written. The whole thing — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/jobs-add

Adds a source to the pipeline. The first argument selects the mode:

First arg Mode What it does
board Board Enable a built-in job board for fetching (persisted; survives sessions).
vacancy / job Single vacancy Hand-add ONE vacancy; it lands unseen and is auto-scored by /jobs-new.
(anything else) / company Company (default) Auto-detect a company's ATS and add it to the database.

Step 0: Route on the first argument

Inspect the first argument the user passed.

  • If it is exactly board → go to Mode B (board).
  • If it is exactly vacancy or job → go to Mode C (single vacancy).
  • Otherwise → go to Mode A (company), treating the argument as the company name / careers URL.

Disambiguation (keyword collision). The keywords board, vacancy, and job can also be real company names ("Board Intelligence", "JobTeaser", "Jobandtalent"). If the first argument is one of those keywords but the surrounding message suggests a real company (e.g. a careers URL is present, or the user typed "add Board Intelligence"), ask once which they meant before routing:

"board" can mean two things here:
  1. Enable a built-in job board (Mode B)
  2. Add the company "Board Intelligence" (Mode A)
Which did you mean?

Do not guess silently. If there is no collision signal, route by the keyword.


Mode B — enable a job board

Boards are built into config/defaults.toml [boards.*] and loaded by config._ALL_JOB_BOARDS. Enabling one persists: it sets the board.enabled flag in the DB (database_supabase.set_board_enabled, surfaced by scripts/sources.py), so the board participates in every future /jobs-new with no env var and no reminder. The JOB_BOARDS env var / --boards flag stays a manual override applied ON TOP of the persisted set for a single run (run_daily.py unions the two). You enable a board by persisting the flag and running one seed fetch.

Read the full file on GitHub · 533 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. 12d ago First seen · 533 lines · 52 tokens per session scan A 476aafb47200

Subscribe to this mod's changes

jobs-add is a command published in the GitHub repository ncalavera/llm-job-pipeline (2 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 5,202 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.