llm-job-pipeline: Command for Claude Code

.claude/commands/jobs-digest.md

jobs-digest is a command for Claude Code from ncalavera/llm-job-pipeline. It costs 13 tokens per session (313 once invoked), scanned A, original, MIT.

A command that sends a daily Telegram message listing unseen job vacancies, with Like and Pass buttons, and records your responses in a database. Telegram is a messaging app, while a database stores the vacancy information.

In plain words
What is it for?
Use it to send a morning job digest and update vacancy statuses from button responses.
Why use it?
It lets you review new vacancies and mark them from Telegram instead of opening the job dashboard each time. It requires a Telegram bot, a PostgreSQL database, and a scheduler such as cron for daily delivery.

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/telegram_digest.py send --dry-run.

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-digest.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-digest

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/ncalavera/llm-job-pipeline/jobs-digest"><img src="https://agentmods.dev/badge/commands/ncalavera/llm-job-pipeline/jobs-digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 313 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 $0.00013 $0.00313
Opus 5 $0.00006 $0.00156
Sonnet 5 $0.00003 $0.00063
Haiku 4.5 $0.00001 $0.00031

Measured 2d ago against content hash 00c7f600c8c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

jobs-digest 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 2d 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/commands/jobs-digest.md · 41 lines

What it actually says

/jobs-digest

The daily driver sends one short message: the Inbox vacancy count and its link. Only preparations matching the current posting and profile count. Run failures remain visible; preparation queues belong to Health. Keep, Pass, Undo, and optional reasons live in the dashboard.

Preview or send

python3 scripts/telegram_digest.py send --dry-run
python3 scripts/telegram_digest.py send

Preview does not send messages or update delivery state. A successful send advances last_digest_at; a failed send leaves it unchanged for retry. The summary does not mark individual vacancies as delivered.

Configuration comes from the existing environment: TELEGRAM_BOT_TOKEN, TELEGRAM_CHAT_ID, the database connection, and DASHBOARD_BASE_URL (or the dashboard_base_url setting). Change the shared bot configuration to route all JobSearch notifications together, including nightly failures and mail notifications.

Optional legacy reports

Only when explicitly requested:

python3 scripts/telegram_digest.py send --details --dry-run
python3 scripts/telegram_digest.py send --details
python3 scripts/telegram_digest.py alert --dry-run

--details retains scored vacancy lists and their delivery claims. alert checks expiring scored roles. Neither is required for daily screening. The digest has no response buttons or polling process; decisions are made in the dashboard.

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. 2d ago Changed · -19 lines · -5 tokens per session 00c7f600c8c6
  2. 12d ago First seen · 60 lines · 18 tokens per session scan A f4d373fa7ba5

Subscribe to this mod's changes

jobs-digest is a command published in the GitHub repository ncalavera/llm-job-pipeline (2 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 313 once invoked, about $0.0001 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.