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 skills/abdulrbasit/job-hunter/commitnpx skills add abdulrbasit/job-hunter --skill commitgit clone --depth 1 https://github.com/abdulrbasit/job-hunterWhat 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 | $0.00028 | $0.00600 |
| Opus 5 | $0.00014 | $0.00300 |
| Sonnet 5 | $0.00006 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
commit 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Commit
Use this skill when preparing a developer commit in this repo.
Goal
Create a clean, intentional commit after verifying that code, tests, configs, and staged files are safe.
Workflow
-
Inspect the worktree.
- Run
git status --short. - Review unstaged and staged diffs for the files you changed.
- Do not revert user changes.
- Run
-
Run preflight checks.
- Tests:
uv run pytest tests/ -q --tb=short - Format check:
uv run ruff format --check job_hunter tests - Lint:
uv run ruff check job_hunter tests - Type check:
uv run ty check job_hunter tests - If formatting fails, run
uv run ruff format job_hunter teststhen rerun format check. Do not hand-format. - If
pyproject.tomlchanged, runuv sync --extra devfirst. - Treat failed tests, lint, or type errors as blockers unless the user explicitly accepts the risk.
- Tests:
-
Stage only specific files.
- Never use
git add .orgit add -A. - Stage files by explicit path.
- Include only files related to the requested change.
- Never use
-
Check staged files.
- Run
git diff --cached --stat. - Run
git diff --cached --name-only. - Confirm no private outputs, generated PDFs, resumes, cover letters, secrets, or unrelated state files are staged.
- Context or skill files may be staged only when the user explicitly requested workflow or agent-behavior changes.
- Run
-
Prepare the commit.
- Propose a concise commit message, 72 characters or fewer.
- Never include
Co-authored-byor any AI attribution trailer. This repo does not use co-author tags regardless of tool defaults. - For version bump commits, the message must be exactly
release: v{VERSION}(e.g.release: v0.14). The release workflow checks for this exact format. - Ask for confirmation before committing.
-
Commit after confirmation.
- Run
git commit -m "<message>". - Show the commit hash and final
git status --short.
- Run
Output Contract
Keep output compact:
- Preflight status.
- Staged file list or stat.
- Commit message.
- Any blockers or warnings.
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.
- 2d ago First seen · 64 lines · 28 tokens per session scan A 000bc24a8389
commit is a skill published in the GitHub repository abdulrbasit/job-hunter (24 stars, last pushed 27d ago), licensed MIT. It adds 28 tokens to every session and 600 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 2026-08-30.
Other skills, from other repositories
career-ops
AI job search command center -- evaluate offers, generate CVs, scan portals, track applications. Use when the user pastes a job URL or JD, asks to scan portals, generate a CV/PDF, track applications, prepare for interviews, draft outreach/emails, or run any career-ops mode.
jobdanmark-search
Make sure to use this skill whenever the user mentions anything related to Danish job listings, job search in Denmark, finding work in Denmark, or job vacancies on Jobdanmark — even if they don't explicitly mention jobdanmark.dk. Also invoke this skill for questions about specific Danish job categories…
jobbank-search
Make sure to use this skill whenever the user mentions anything related to job searching on Akademikernes Jobbank, jobbank.dk, or looking for academic or highly educated positions in Denmark — even if they don't mention jobbank.dk explicitly. Also invoke this skill for questions about Danish job listings, graduate…
job-application-assistant
Assists with job applications: evaluating job postings, tailoring CVs, writing cover letters, and preparing for interviews. Triggers on keywords like: job posting, job application, CV, cover letter, resume, interview prep, job fit, career, application, apply, ansøgning, stilling.
decision-heuristics
当用户在重大选择上纠结（换工作/买房/搬城/合伙/结婚）、列了利弊表还是拿不定主意时调用。 核心理念: 无法决定就答否; 三个重大决定(住哪/和谁/做什么)值得花一两年; 两个均等选择选短期更痛苦的路。 不适用于: 日常琐碎选择（晚饭吃什么）、信息查询。 Triggers: 纠结/拿不定主意/要不要/该不该/利弊/decision/hesitate/should I.
principal-agent
当用户选择职业/组织/合作方式、困惑「为什么大公司磨洋工/小公司拼命」「该不该自己干」时调用。 核心理念: 委托人(主人)会把事做好, 代理人会为自己利益优化; 收益与创造价值绑得越紧, 越像委托人; 别让媒体洗脑你需要代理人。 不适用于: 具体薪酬谈判数字、组织架构设计细节。 Triggers: 激励/代理/主人/打工 vs 创业/利益绑定/principal/agent/incentive.