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.
curl -O https://raw.githubusercontent.com/ncalavera/llm-job-pipeline/main/AGENTS.mdgit clone --depth 1 https://github.com/ncalavera/llm-job-pipelineWrote 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/instructions/ncalavera/llm-job-pipeline/agents-md)<a href="https://agentmods.dev/instructions/ncalavera/llm-job-pipeline/agents-md"><img src="https://agentmods.dev/badge/instructions/ncalavera/llm-job-pipeline/agents-md/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/instructions/ncalavera/llm-job-pipeline/agents-md"><img src="https://agentmods.dev/badge/instructions/ncalavera/llm-job-pipeline/agents-md.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 | $0.02450 | $0.02450 |
| Opus 5.5 | $0.00980 | $0.00980 |
| Sonnet 5.5 | $0.00490 | $0.00490 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
llm-job-pipeline AGENTS.md 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
This repo is agent-agnostic. It works with Claude Code, Codex, or any coding agent that can run shell commands and follow markdown runbooks.
Read STRATEGY.md first (hard rule)
Before ANY product work — a feature, a prompt or runbook change, a new source,
board, or flag — read STRATEGY.md. It is the decision frame: three goals and
the guardrails every change must pass. If a request or ticket conflicts with
STRATEGY.md, STOP and ask the user which wins; do not proceed on the conflicting
path. A change that fails a guardrail gets rewritten or rejected, however useful
it is to one user.
Where the runbooks live
.claude/commands/*.md are plain-markdown, step-by-step runbooks — they are
NOT Claude-specific despite the folder name. If you are Claude Code they load
as slash commands automatically; any other agent should open the file and
follow it verbatim when the user asks for that workflow:
| User asks for | Runbook |
|---|---|
| first-time setup, daily fetch + prepare, resume, deploy | .claude/commands/jobs-new.md |
| review liked vacancies, archive low scores, terminal triage | .claude/commands/jobs-review.md |
| check scoring quality against your own labels (golden set) | .claude/commands/jobs-eval.md |
| add a company or job board | .claude/commands/jobs-add.md |
| update scoring rules or candidate profile | .claude/commands/jobs-profile.md |
| Telegram digest (send / poll) | .claude/commands/jobs-digest.md |
| pull latest code, apply DB migrations | .claude/commands/jobs-update.md |
The daily loop (jobs-new.md) is driven by scripts/run_daily.py — a plain
Python state machine that owns stage ORDER, checkpoints, the heartbeat and the
publish gate. Any agent runs python3 scripts/run_daily.py, watches for exit
code 10 (a GATE), does the printed evidence-preparation task, then
--resumes — repeating until exit 0. The agent never orders the stages; it only
answers the gates. Exit codes: 0 done, 10 gate, 20 abort, 30 stage error.
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.
- 1mo ago Changed · +11 lines · +97 tokens per session 0fedbb9222c4
- 2mo ago Changed · -1 tokens per session e60757ce5db3
- 2mo ago First seen · 168 lines · 2,354 tokens per session scan A 4e9b54f90233
llm-job-pipeline AGENTS.md is an instructions file published in the GitHub repository ncalavera/llm-job-pipeline (2 stars, last pushed 16d ago), licensed MIT. It adds 2,450 tokens to every session, about $0.0098 per session on Opus 5.5. 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.
llm-job-pipeline AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| llm-job-pipeline AGENTS.mdncalavera/llm-job-pipeline | Instructions file | 2 | 16d ago | MIT | A | 2,450 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |