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-cvgit 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-cv)<a href="https://agentmods.dev/skills/akbardevop/ai-job-agent/job-cv"><img src="https://agentmods.dev/badge/skills/akbardevop/ai-job-agent/job-cv/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-cv"><img src="https://agentmods.dev/badge/skills/akbardevop/ai-job-agent/job-cv.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 | $0.00199 | $0.02351 |
| Opus 5 | $0.00100 | $0.01175 |
| Sonnet 5 | $0.00040 | $0.00470 |
| Haiku 4.5 | $0.00020 | $0.00235 |
Grade A, and why
job-cv 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 12d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job CV
A skill (not an API call) for producing a tailored, ATS-friendly PDF resume for one specific posting. Claude does the rewriting. A small Node script renders the approved markdown to PDF via headless Chromium (Playwright). No LaTeX, no pandoc, no extra deps.
This pairs with /job-outreach (the cold-email skill): a tailored CV in hand makes the outreach concrete. It also feeds /job-apply — most ATS forms accept a custom resume upload.
Repo location
$AI_JOB_AGENT_ROOT → ~/.claude/skills/ai-job-agent/ → REPO_PATH marker file → ~/ai-job-agent/.
Prerequisites
Before drafting anything:
-
A base CV exists. Look in this order:
$AI_JOB_AGENT_ROOT/cv.md(preferred)$AI_JOB_AGENT_ROOT/config/cv.md- Extract a CV-shaped markdown from
$AI_JOB_AGENT_ROOT/config/candidate-profile.md(sections: identity, education, experience, projects, skills) and write it to$AI_JOB_AGENT_ROOT/cv.mdso future runs reuse it. Confirm with the user before writing.
If none of the above is reachable: tell the user to run
/job-setupfirst and stop. -
Chromium is reachable for Playwright. If
npm testor a previous run errored withExecutable doesn't exist, tell the user:npx playwright install chromiumthen retry. Stop until set up.
-
output/exists at$AI_JOB_AGENT_ROOT/output/. If not, create it (mkdir -p).
Workflow
Step 1 — Understand the target
Parse $ARGUMENTS. It might be:
- A direct job URL (LinkedIn, Greenhouse, Lever, Ashby, Jobvite, careers page)
- Pasted JD text in the user's message
- A company name + role ("backend intern at Stripe" — fetch the listing yourself)
If only a company is given and no URL, search for the listing first, then confirm the exact posting with the user before continuing.
Step 2 — Read the JD
- URL → use
WebFetchto pull the page. If the result is a JS-only shell with no JD text, fall back toWebSearchfor the same role at the same company and try the second hit. - Pasted text → use as-is.
- Extract: company, role title, location / work-auth notes, 3-7 must-have skills (the ones most repeated or in the title), 3-5 nice-to-haves, tone (research-y? startup-y? enterprise?).
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.
- 12d ago First seen · 180 lines · 199 tokens per session scan A 9b3b4d20833f
job-cv is a skill published in the GitHub repository AkbarDevop/ai-job-agent (55 stars, last pushed 4mo ago), licensed MIT. It adds 199 tokens to every session and 2,351 once invoked, about $0.0010 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
critic-loop
Run the mandatory 3-round CV review loop with the Critico — autonomously, without going through the Capitano. For each round you spawn a FRESH CRITICO-S session (same N as your Scrittore session: SCRITTORE-2 → CRITICO-S2), send PDF + JD, wait for the structured verdict, kill the Critic, correct the CV, regenerate the…
parse-cv
Pre-process a CV/profile file (PDF, DOCX, ODT, RTF) into plain text BEFORE feeding it to the LLM context. Reduces token cost by 5-10x on long CVs and yields more reliable extraction than reading binary PDFs directly via multimodal vision. The Assistente calls this skill on every uploaded document in…
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…
resume-tuning
An interactive resume-writing workflow that turns an existing resume or spoken work history into a tailored PDF resume. It can adapt the content to a job description and check whether applicant-tracking systems can read it.
atsscore
Jobgru pipeline Phase 2b — score local resume PDFs against job Skills in the sheet. Writes column I (ATS score) and column J (Suggestions on Resume). Runs in parallel with LeadGru after Phase 1. Python-only scoring, rule-based suggestions, no LLM. Auto-on when data/resumes/ has PDFs; off when folder empty or prompt…
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…