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/review)<a href="https://agentmods.dev/skills/alwaysmap/jobs4me/review"><img src="https://agentmods.dev/badge/skills/alwaysmap/jobs4me/review.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 | $0.00129 | $0.02584 |
| Opus 5 | $0.00064 | $0.01292 |
| Sonnet 5 | $0.00026 | $0.00517 |
| Haiku 4.5 | $0.00013 | $0.00258 |
Grade A, and why
review 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 8d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review / Triage Session
Shell setup: The tracker script auto-detects the workspace directory. If needed, set JFM_DIR environment variable or use --dir.
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.
Walk the user through their tracked roles one at a time, grouped by what needs attention. This is a conversational triage — present a role, get a quick decision, apply it, kick off background work, move on.
First Review Calibration
Before starting, check if all roles in tracker.yaml have stage: suggested (no roles in maybe, applied, interviewing, or other non-suggested stages). If so, this is likely the user's first review session. Frame it as calibration:
"This first review helps me learn what you actually want. For each role, tell me what you think — your reactions help the agent get smarter. Be honest about why you like or dislike each one."
This sets the expectation that their feedback is training data, not just triage.
Arguments
/jfm:review accepts an optional stage filter as its argument:
| Input | What gets queued |
|---|---|
/jfm:review |
Everything that needs attention (default priority order) |
/jfm:review all |
Same as no argument |
/jfm:review suggested |
Only new suggestions |
/jfm:review maybe |
Only roles marked as interesting |
/jfm:review applied |
Only roles in applied stage |
/jfm:review interviewing |
Only roles in interview stage |
/jfm:review stale |
Maybes >7 days + applied >14 days (things going cold) |
The user can also use natural language: "review what's new", "triage my suggestions", "what needs attention in applied".
Start a Review Session
- Read
tracker.yaml,profile.yaml, andfilters.yaml - Build the review queue based on the filter (or full priority order if no filter)
- Tell the user what's in the queue:
{N} roles to review{stage filter note, e.g., " (suggested only)"} — let's walk through them.
For each one I'll show you the summary. You can say:
- yes / interested — move to Maybe
- apply — mark as Applied
- advance — move to the next stage (Maybe→Applied, Applied→Interviewing)
- skip — leave it, come back later
- decline {reason} — pass on it
- tell me more — I'll pull up the full JD and assessment
Ready?
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.
- 8d ago First seen · 221 lines · 129 tokens per session scan A 2f296d1e19a3
review is a skill published in the GitHub repository alwaysmap/jobs4me (2 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 2,584 once invoked, about $0.0006 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
job-application-agent
Finds, evaluates, fills, submits, and tracks a candidate's own job applications using a verified resume, evidence-based targeting, secure local profile storage, and browser automation. Use for onboarding or migrating a job-search profile, searching active roles, assessing a posting, applying to an authorized URL or…
apply
Apply to a single job (URL or pasted page) with fit review, or score and apply the job links pasted into an apply campaign when no argument is given.
scan-inbox
Classify unscanned mailbox messages, fuzzy-match each to an existing application, and write the proposal back. The user approves in /inbox.
resume-campaign
Resume a paused JobPilot campaign by id. Re-flips the campaign to inprogress and replays the apply loop on any remaining approved jobs without re-asking for fit confirmation.
autopilot-jobhunt
Run a job hunt in one agentic pass — scan configured company careers pages, score postings against the user's resume, draft a tailored resume + cover letter per chosen role (never applies), and export matches. Trigger when the user says /autopilot-jobhunt or asks to scan/find jobs or draft an application.
auto-job-apply
A job-application workflow that compares a job description with a resume and assigns an A, B, or C match grade.