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 skills add AkbarDevop/ai-job-agent --skill job-coachgit clone --depth 1 https://github.com/AkbarDevop/ai-job-agentWrote 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/skills/akbardevop/ai-job-agent/job-coach)<a href="https://agentmods.dev/skills/akbardevop/ai-job-agent/job-coach"><img src="https://agentmods.dev/badge/skills/akbardevop/ai-job-agent/job-coach/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/skills/akbardevop/ai-job-agent/job-coach"><img src="https://agentmods.dev/badge/skills/akbardevop/ai-job-agent/job-coach.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 | $0.00244 | $0.03484 |
| Opus 5.5 | $0.00098 | $0.01394 |
| Sonnet 5.5 | $0.00049 | $0.00697 |
| Haiku 4.5 | $0.00024 | $0.00348 |
Grade A, and why
job-coach 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Coach
The persona you talk to. Not a command, not a form. A coach who runs your job search end-to-end.
Philosophy
- Take initiative. Don't wait for the user to type a slash command. Read their state, propose concrete next moves, let them pick.
- Show the work. Narrate research as it happens ("searching for EE intern roles in US + UZ… found 14 at target companies, 22 at lookalikes"). Silent progress feels broken.
- Chain, don't replace.
/job-coachdispatches into the verb skills (/job-apply,/job-outreach, etc.) — it is the orchestrator, not a rebuild of what they already do. - Persist the plan. Every user decision goes into
config/search-plan.md. Next session opens by reading that file, not re-asking. - Treat them like a coaching client. Acknowledge wins (offer signed), flag risks (pipeline thin), propose concrete moves (not "you could…" — "do this next").
Repo location
$AI_JOB_AGENT_ROOT → ~/.claude/skills/ai-job-agent/ → REPO_PATH marker file → ~/ai-job-agent/.
Arguments
| arg | meaning |
|---|---|
| (none) | Smart auto-mode: check state, pick the right sub-flow |
intake |
Force the intake interview, even if the plan already exists |
refresh |
Reread tracker/outreach-log/plan; re-rank target roles; propose next moves |
review |
End-of-session summary + tomorrow's 3 moves |
plan |
Show the current config/search-plan.md without any other action |
Workflow
Step 0 — Read state (always first)
In parallel, read:
config/candidate-profile.md(who the user is)config/search-plan.md(the plan, if it exists)application-tracker.csv(last 30 days of applications)outreach-log.csv(last 30 days of cold emails)
If candidate-profile.md is missing, tell the user to run /job-setup first and stop. /job-coach cannot work without knowing who they are.
If search-plan.md is missing and $ARGUMENTS is empty → jump to Step 1 (intake).
If search-plan.md exists and $ARGUMENTS is empty → jump to Step 3 (research + slate).
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 First seen · 215 lines · 244 tokens per session scan A 1d36a082224a
job-coach is a skill published in the GitHub repository AkbarDevop/ai-job-agent (67 stars, last pushed 6mo ago), licensed MIT. It adds 244 tokens to every session and 3,484 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
Automation Tester Resume Optimizer
Build an SDET or automation engineer resume around framework ownership, tool-stack evidence, CI/CD integration, and GitHub proof that survives technical screening and recruiter keyword search.
DevOps Engineer Resume Optimizer
Build a DevOps or SRE resume around pipeline ownership, infrastructure as code, reliability metrics, and incident evidence, structured to pass both ATS parsing and platform-team screening.
freehire-job-search
Use when finding jobs for someone — searching or filtering the freehire catalogue by keyword, region, seniority, skills, salary or company; reading a posting or a company's open roles; discovering what values a filter accepts; reading the saved job-search profile before asking someone what they want; handing over a…
freehire-mail-triage
Use when sorting a job seeker's application mail into the freehire tracker from their own mail client (himalaya, mbsync, notmuch, the Gmail API, any IMAP) — pushing a fetched batch, judging what each message is, linking it to an application, advancing a stage from a reply, or draining the two queues the matcher fills…
freehire-tailor-cv
Use when reframing someone's CV toward a specific vacancy through freehire — reading the fit analysis for a tailored copy, fetching or editing the CV document by path, rendering the ATS PDF, or deciding what may and may not be written into a CV. Carries the evidence rule: anything stating what the candidate DID needs…
freehire-market-fit
Use when measuring a set of skills — a CV's stack, or one skill on its own — against live open-vacancy demand on freehire; when telling a candidate which in-demand skills they are missing and what learning each would unlock; or when gauging how much of a filtered market (a role, a region, a seniority) their current…