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/assess)<a href="https://agentmods.dev/skills/alwaysmap/jobs4me/assess"><img src="https://agentmods.dev/badge/skills/alwaysmap/jobs4me/assess.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 | $0.00084 | $0.01246 |
| Opus 5 | $0.00042 | $0.00623 |
| Sonnet 5 | $0.00017 | $0.00249 |
| Haiku 4.5 | $0.00008 | $0.00125 |
Grade A, and why
assess 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 7d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess a Job Posting
Shell setup: Always export JFM_DIR='<workspace path>' (single quotes) before running tracker commands. The script refuses to operate if it can't resolve a real workspace.
Read ../search/references/routing.md before processing any user message — it defines how to decompose compound messages and where to route each type of input.
Assess a specific job posting against the user's profile.
Steps
-
Read
profile.yaml,archetypes.yaml, andfilters.yaml -
Fetch the URL provided by the user using WebFetch. Use Haiku for simple JD extraction from URLs if delegating to a sub-agent.
-
Extract the job description from the page
-
Run a full fit assessment using the search skill's fit assessment framework
-
Present the assessment to the user (Recommendation, Gaps, Positive Fit)
-
Ask if they want to add it to the tracker — or decline it immediately
-
If adding, add via the tracker script:
node ${CLAUDE_PLUGIN_ROOT}/scripts/tracker.js add --json '{"company":"...","role":"...","url":"...","archetype":"...","stage":"suggested","agent_summary":"..."}' -
Get the file paths for the new entry and save the JD:
Always save the JD locally — Greenhouse / Lever / Ashby postings are removed once roles close, and the user needs the JD for cover letters, prep, and a record of what they applied for. Save the JD even when declining: declined JDs feed the decline-pattern learning loop.
node ${CLAUDE_PLUGIN_ROOT}/scripts/tracker.js paths --id <id>This returns
role_dirandcompany_dir. Save the JD to{role_dir}/jd.md. Create the directories if they don't exist (mkdir -p).After saving, use
present_filesto share the board with the user, then tell them what was created:Added to tracker — {Company} / {Role} JD saved —
{role_dir}/jd.mdYour board has been updated — refresh to see it. -
If declining (user says "not interested", "pass", "decline", etc.):
- If already added to tracker, decline it:
node ${CLAUDE_PLUGIN_ROOT}/scripts/tracker.js decline --id <id> --reason "reason text" - If not yet added, add it as declined so the reason is tracked:
node ${CLAUDE_PLUGIN_ROOT}/scripts/tracker.js add --json '{"company":"...","role":"...","url":"...","stage":"declined","decision":{"proceed":"no","reason":"reason text"}}' - Always run decline pattern learning (see
../search/references/decline-learning.md): check if this decline suggests a new pattern or refines an existing one. If so:
Tell the user what filter change was made (if any). Usenode ${CLAUDE_PLUGIN_ROOT}/scripts/tracker.js add-decline-pattern --pattern "Pattern description" --learned-from "Company Name"present_filesto shareKanban/index.html, then tell the user: "Your board has been updated."
- If already added to tracker, decline it:
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.
- 7d ago First seen · 91 lines · 84 tokens per session scan A 7757de351ca1
assess is a skill published in the GitHub repository alwaysmap/jobs4me (2 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,246 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.