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 jain777/jobclaw-skills --skill apply-to-jobgit clone --depth 1 https://github.com/jain777/jobclaw-skillsWrote 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/jain777/jobclaw-skills/apply-to-job)<a href="https://agentmods.dev/skills/jain777/jobclaw-skills/apply-to-job"><img src="https://agentmods.dev/badge/skills/jain777/jobclaw-skills/apply-to-job/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/jain777/jobclaw-skills/apply-to-job"><img src="https://agentmods.dev/badge/skills/jain777/jobclaw-skills/apply-to-job.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 | $0.00085 | $0.01097 |
| Opus 5 | $0.00043 | $0.00549 |
| Sonnet 5 | $0.00017 | $0.00219 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
apply-to-job 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apply-to-job
One command to turn a job into a ready-to-submit application package. This skill orchestrates the
other skills (it invokes them in order) — it does not re-implement them. Stage map + each skill's role:
../../knowledge/pipeline.md. Hard rules: ../_shared/RULES.md.
Input
A job, supplied any way: a URL, pasted JD text, or a job_id from jobs/found-<date>.json.
If none is given, read jobs/current.json; if that's absent too, ask for the job.
Mode
Ask once at the start (or accept --mode auto|review):
"Run this in auto-pilot (I run the whole chain and only stop at the apply/skip call and before anything is sent) or review (I check with you before each step)?"
Default to review if the user doesn't choose. Both modes obey the same guardrails below.
Chain
- Preflight (notify the user before starting). Run
python3 scripts/doctor.py. If rendercv is missing, tell the user now (it's needed for the resume PDF later in the chain) and offer the one-time install — don't discover it mid-chain. Then checkprofile/master-profile.md: if missing → run/build-profilefirst (or stop and say so). - Capture the job once. Resolve the JD (fetch the URL / use the pasted text / look up the
job_id) and writejobs/current.json={company, role, url, job_id, jd_text, region, source, captured_at}. Every downstream skill reads this — the JD is supplied once (RULES §6). score-fit. Run it againstjobs/current.json.- Skip / low fit: in auto mode, stop and report the one-line reason (offer: "apply anyway?"); in review mode, ask whether to proceed.
- Apply / Apply-if-tailored: continue.
tailor-resume. Produces the tailored resume PDF (+ md + sidecars) and runs thereview-renderQA loop. Relay any ATS warning.write-cover-letter. Region-aware (US: role-dependent; IN: short-form often enough — follow the region pack). Skip only if the user opts out.answer-application-questions. Only if the user provides the form's questions (paste or a JSON schema). If no form is available yet, note it and move on — the answers come at submit time.- Assemble + STOP. Present the package: resume PDF path, cover letter, any answers, and the apply URL. Do not submit, send, or auto-fill any portal — that's the human's action (or the JobClaw agent's, behind its own guardrails).
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 · 57 lines · 85 tokens per session scan A 19949032f891
apply-to-job is a skill published in the GitHub repository jain777/jobclaw-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 1,097 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.