Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/instructions/colophon-group/jobseek/agents-md)<a href="https://agentmods.dev/instructions/colophon-group/jobseek/agents-md"><img src="https://agentmods.dev/badge/instructions/colophon-group/jobseek/agents-md.svg" alt="Measured on agentmods" 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 | $0.03643 | $0.03643 |
| Opus 5 | $0.01821 | $0.01821 |
| Sonnet 5 | $0.00729 | $0.00729 |
| Haiku 4.5 | $0.00364 | $0.00364 |
Grade A, and why
jobseek 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 6d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Jobseek
Instructions for developer agents working on this repository.
Project Overview
Jobseek monitors company career pages for new job postings. Companies are configured via CSV files in apps/crawler/data/. A Python crawler monitors boards and extracts job details. A Next.js frontend serves the data.
Repository Structure
/
├── apps/
│ ├── web/ # Next.js 15 frontend (TypeScript, Drizzle ORM, Lingui i18n)
│ └── crawler/ # Python crawler (asyncpg, httpx, structlog, redis)
│ ├── data/
│ │ ├── companies.csv # Company registry (slug, name, website, logos)
│ │ ├── boards.csv # Board configs (monitor + scraper per board)
│ │ └── images/ # Logo/icon staging area, uploaded to R2 by CI
│ └── src/
│ ├── core/ # Pure business logic (monitors + scrapers)
│ ├── workers/ # Worker pipeline (claim from Redis, dispatch)
│ ├── processing/ # Board/scrape processing, CPU work, R2 staging
│ ├── queries/ # SQL queries for local Postgres
│ ├── redis_queue.py # Lua-backed claim/enqueue/reschedule
│ ├── lua/ # Redis Lua scripts
│ ├── exporter.py # CDC: local Postgres -> Typesense
│ ├── typesense_client.py # Shared Typesense client (lazy, feature-flagged)
│ ├── sync.py # CSV -> DB + Redis + Typesense taxonomy sync
│ ├── cli.py # Entry point (crawler run/export/drain/sync/board/...)
│ ├── config.py # Settings
│ └── labeller/ # Daily labelled-postings ops routine
│ ├── cli.py # labeller = src.labeller.cli:main
│ ├── normalize.py # deterministic HTML normalizer
│ ├── blocks.py # HTML -> block list
│ ├── validate.py # JSON Schema + custom validators
│ ├── render.py # Jinja task-input renderer
│ ├── sampling.py # diverse per-company posting sample
│ ├── prepare.py # load posting + normalize + blocks
│ ├── merge.py # assemble subagent outputs into posting.json
│ ├── upload.py # HuggingFace dataset push
│ ├── prompts/tasks/*.md.j2 # per-task Jinja templates
│ └── schemas/ # per-task + posting JSON Schemas
├── scripts/ # Monorepo-wide operator/dev scripts; app-local scripts live under apps/*/scripts/
│ ├── typesense-setup.py # Create/recreate Typesense collections + aliases
│ └── typesense-backfill-local.py # One-shot backfill from Postgres to Typesense
├── docs/ # Architecture documentation
│ ├── 11-typesense.md # Typesense deployment + architecture reference
│ ├── 12-typesense-benchmarks.md # Performance benchmarks
│ ├── 14-error-review-routine.md # Daily crawler error-review routine spec
│ ├── 15-data-sampling-routine.md # Daily labelled-postings routine spec
│ ├── 16-murmur-codex-mcp-transition.md # Murmur Codex MCP transition plan
│ ├── 17-codex-migration-verification-runbook.md # Codex pilot verification
│ └── 18-codex-automation-deployment.md # Hetzner Codex runner deployment + maintenance
└── .github/workflows/ # CI + agent automation
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.
- 6d ago First seen · 240 lines · 3,643 tokens per session scan A 53694fcdded1
jobseek AGENTS.md is an instructions file published in the GitHub repository colophon-group/jobseek (190 stars, last pushed 2d ago), licensed MIT. It adds 3,643 tokens to every session, about $0.0182 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 instructions, from other repositories
freehire AGENTS.md
AGENTS.md instructions for strelov1/freehire, covering agents.md, working principles, what this is, layout and commands.
freehire CLAUDE.md
Claude Code instructions for strelov1/freehire, a project described as: freehire — the open-source search engine for job seekers.
openhire CLAUDE.md
Claude Code instructions for gzchenhao/openhire, covering claude.md — openhire 工作约定（每个会话必读）, 新会话恢复指引（开工前先做这三步）, 发布状态（v0.1 已上线 + 上架官方 registry · 2026-07-15）, 常设工作制度（持续遵守） and 三条隐私红线（ci 强制，永不可破）.
please-hire-me CLAUDE.md
Instructions for alecswang/please-hire-me, covering please-hire-me — agent entry point (read this first), setup, step by step, rules during onboarding, what this is and repo layout.
ai-job-agent CLAUDE.md
Instructions for AkbarDevop/ai-job-agent, covering ai job application agent - claude code instructions, bundled skills, unified mode — npm run agent, npm scripts and output locations (all gitignored).
Resume-Builder CLAUDE.md
Instructions for jananthan30/Resume-Builder, covering resume builder - project context, quick start, option 1: claude code custom commands (recommended), resume only - dual optimized and cover letter only.