Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add alwaysmap/jobs4me/plugin install jfmWrote 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/alwaysmap/jobs4me/search)<a href="https://agentmods.dev/skills/alwaysmap/jobs4me/search"><img src="https://agentmods.dev/badge/skills/alwaysmap/jobs4me/search.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 5.1 | $0.00078 | $0.03002 |
| Opus 5 | $0.00039 | $0.01501 |
| Sonnet 5 | $0.00016 | $0.00600 |
| Haiku 4.5 | $0.00008 | $0.00300 |
Grade A, and why
search 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 6d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Search Agent
Autonomous job search, fit assessment, and learning loop for a configured job seeker.
Files
| File | Loaded when |
|---|---|
SKILL.md (this file) |
Always |
references/routing.md |
First — before processing any user message. Decomposes compound input and pins the no-memory rule. |
references/career-page-search.md |
Phase 1 — career page scraping, Chrome MCP fallback, ATS URL patterns. |
references/liveness.md |
Phase 2 / Phase 3 boundary — MANDATORY before any add of a suggested entry. |
references/fit-assessment.md |
Phase 2 Step B — the structured rubric for sub-agent fit assessments. |
references/yaml-writing.md |
Phase 3 — write protocol, formatting rules, dedup table. |
references/data-safety.md |
Phase 3 — referenced from yaml-writing.md; mandatory before any file write. |
references/yaml-schema.md |
Phase 3 / debugging — full schema for tracker / profile / archetypes / filters. |
references/brief-format.md |
Phase 3 end — search brief template. |
references/decline-learning.md |
After any decline (per-decline or per-batch). |
references/model-selection.md |
Whenever spawning sub-agents. |
Shell Setup
Always export JFM_DIR='<workspace path>' (single quotes) before running any tracker command. The script refuses to operate on a phantom workspace, so setting this up front avoids silent writes to the wrong directory when the path contains spaces or special shell characters. Dependencies are vendored — no npm install needed.
export JFM_DIR='<workspace path>'
Routing
Read references/routing.md before processing any user message. It defines how to decompose compound messages, where each type of user input should be routed, and the rule against saving job search data to Claude memory.
Core Files
Always read these fresh at the start of each operation — the user may have edited them by hand:
- profile.yaml — who the user is: resume URLs, portfolio, preferences
- archetypes.yaml — the types of roles they're targeting
- filters.yaml — company include/exclude/watch lists, sources, decline patterns
- tracker.yaml — all applications with stage, dates, agent summary
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/brief-format.md 3.0 KB
- references/career-page-search.md 4.8 KB
- references/data-safety.md 6.1 KB
- references/decline-learning.md 3.0 KB
- references/fit-assessment.md 4.8 KB
- references/liveness.md 2.8 KB
- references/model-selection.md 1020 B
- references/routing.md 5.4 KB
- references/yaml-schema.md 10.0 KB
- references/yaml-writing.md 2.6 KB
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.
- 6d ago First seen · 234 lines · 78 tokens per session scan A 26c709da194b
search is a skill published in the GitHub repository alwaysmap/jobs4me (2 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 3,002 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
swissdevjobs
Search nine job boards across eight countries — the salary-transparent devitjobs family, jobs.ch and jobup.ch (all Swiss industries), and MyCareersFuture (Singapore IT) — and help the user apply. Handles the native apply form, direct-email postings, and third-party ATS postings (driven with a browser MCP). Trigger…
tailor-resume
Choose the best existing resume base/variant for a job, or create a new tailored variant when nothing fits.
auto-apply
Search a job board and autonomously apply to matching jobs one at a time, until paused, exhausted, or the max-applications cap is hit.
teaser-video
Film, cut, and deliver a short teaser/demo video of any app by driving it with Playwright and editing with ffmpeg - storyboard, authenticated capture, PII review, animated title cards, MP4 + GIF. Use for "make a teaser", "record a demo video", "product launch video", "screen recording for the README".
pilot
One autonomous Pilot cycle - fetch the agenda, execute the top item, journal, exit. Injected by the terminal host - not for manual invocation loops.
scan-inbox
Classify unscanned mailbox messages, fuzzy-match each to an existing application, and write the proposal back. The user approves in /inbox.