Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/abdulrbasit/job-hunter/agents-mdgit clone --depth 1 https://github.com/abdulrbasit/job-hunterWrote 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/abdulrbasit/job-hunter/agents-md)<a href="https://agentmods.dev/instructions/abdulrbasit/job-hunter/agents-md"><img src="https://agentmods.dev/badge/instructions/abdulrbasit/job-hunter/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 | $0.01093 | $0.01093 |
| Opus 5 | $0.00547 | $0.00547 |
| Sonnet 5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
job-hunter 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 5d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Hunter
This is the agent context source of truth for the product repo. CLAUDE.md and any other per-agent files defer here. Keep durable operating context in this file, skills, config, or code; do not add separate architecture docs.
This repo combines the Python engine (job_hunter/) and the agent skill layer (.claude/skills/, .agents/skills/).
Execution Modes
| Mode | What runs | When to use |
|---|---|---|
agent |
Agent skills handle scoring, tailoring, cover letters. Python prepares context. | Default interactive review. |
llm-api |
Full autonomous pipeline; LLM APIs called directly inside Python. | Unattended runs and GitHub Actions. |
Set mode: in config/job_hunter.yml.
Repo Map
job_hunter/: Python package, CLI, pipeline, source adapters, LLM API mode..claude/skills/: skills for Claude Code (mirrored to.agents/skills/for Codex).config/job_hunter.yml: user-editable machine config.config/schemas/job_hunter.schema.json: schema forjob_hunter.yml.job_hunter/templates/workspace/profile/: canonical starter profile and resume templates.examples/profile/: filled fictional examples; not a template source.outputs/state/jobs.db: SQLite — single source of truth for all job state (URL dedup, scraped candidates, application lifecycle).docs/architecture.md: current package ownership, dependency boundaries, pipeline, state, and template architecture.
Skills
/job-hunter job search command center (batch, one, finalize, screen,
tailor, score, research, interview, outreach, stories, linkedin)
/linkedin LinkedIn content center (ideas, draft, engage, network)
/setup workspace setup center (onboard, doctor, region, style, stories)
Developer contributor context:
/commit preflight checks, safe staging, and commit format
Use /commit before developer commits. It still requires full preflight:
python -m pytest tests/ -q --tb=short
python -m ruff format --check job_hunter tests .github/scripts
python -m ruff check job_hunter tests .github/scripts
ty check job_hunter tests
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.
- 5d ago First seen · 103 lines · 1,093 tokens per session scan A 6ff4c8fe34e9
job-hunter AGENTS.md is an instructions file published in the GitHub repository abdulrbasit/job-hunter (24 stars, last pushed 1mo ago), licensed MIT. It adds 1,093 tokens to every session, about $0.0055 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
ai-job-search CLAUDE.md
Claude Code instructions for MadsLorentzen/ai-job-search, covering job application assistant for [yourname], role, candidate profile, identity and education.
career-ops CLAUDE.md
Instructions for santifer/career-ops, a project described as: Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…).
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).
spellbook AGENTS.md
AGENTS.md instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
vrchat-mcp AGENTS.md
AGENTS.md instructions for BASIC-BIT/vrchat-mcp, covering agents, tool ergonomics goals (distilled), curated output philosophy, specific notes (current direction) and caching considerations (planned).
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).