Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AkbarDevop/ai-job-agentnpx agentmods add skills/akbardevop/ai-job-agent/job-triageWrote 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-triage)<a href="https://agentmods.dev/skills/akbardevop/ai-job-agent/job-triage"><img src="https://agentmods.dev/badge/skills/akbardevop/ai-job-agent/job-triage/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-triage"><img src="https://agentmods.dev/badge/skills/akbardevop/ai-job-agent/job-triage.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 | $0.00098 | $0.01741 |
| Opus 5 | $0.00049 | $0.00870 |
| Sonnet 5 | $0.00020 | $0.00348 |
| Haiku 4.5 | $0.00010 | $0.00174 |
Grade A, and why
job-triage scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:${OUTLOOK_PORT:-9224}/json/version >/dev/null && echo OK || echo MISSING How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Triage
Thin wrapper around scripts/outlook-triage.js that runs a search, classifies results locally, and presents them as a table. The underlying script requires a Chrome instance running with --remote-debugging-port=9224 and Outlook Web already logged in.
Repo location
Same resolution as /job-apply: $AI_JOB_AGENT_ROOT → ~/.claude/skills/ai-job-agent/ → REPO_PATH marker file → ~/ai-job-agent/.
Prerequisites
Before doing anything, verify Chrome is reachable:
curl -s http://127.0.0.1:${OUTLOOK_PORT:-9224}/json/version >/dev/null && echo OK || echo MISSING
If MISSING, tell the user:
Start Chrome with remote debugging and open Outlook Web first:
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \ --remote-debugging-port=9224 \ --user-data-dir=/tmp/outlook-triage-profileThen navigate to outlook.office.com and log in. Rerun /job-triage.
Stop until they confirm.
Workflow
1. Run the search
cd "$AI_JOB_AGENT_ROOT"
node scripts/outlook-triage.js --port "${OUTLOOK_PORT:-9224}" search "$QUERY"
Default query: application status. If the user passes a different query via $ARGUMENTS, use that instead.
The script returns a JSON array of result objects with idx, aria, text, unread, flagged, pinned.
2. Classify each result
Run each text through these regex rules in order — first match wins:
| Class | Regex (case-insensitive) |
|---|---|
| interview_invite | `interview |
| action_required | `assessment |
| rejection | `unfortunately |
| confirmation | `received your application |
| recruiter_outreach | `recruiter |
| other | (default fallback) |
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 · 153 lines · 98 tokens per session scan A ebfb8fea6e19
job-triage is a skill published in the GitHub repository AkbarDevop/ai-job-agent (55 stars, last pushed 4mo ago), licensed MIT. It adds 98 tokens to every session and 1,741 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
jobgru-setup
Jobgru first-time setup, help, and health check. Use when the user says Jobgru setup, first time, configure sheet, update sheet link, add resume, Jobgru help, or Jobgru check. Handles venv, pip install, config/sheet.json, resume PDF placement, and sheet profile writes — user only manually copies the Google Sheet…
Automation Tester Resume Optimizer
Build an SDET or automation engineer resume around framework ownership, tool-stack evidence, CI/CD integration, and GitHub proof that survives technical screening and recruiter keyword search.
mentor-patterns
The six patterns the Mentor hunts in the records to decide WHEN to speak. Silence is the default; only a real, recurring pattern earns a word. This skill gives the canonical detection method for each pattern (DB query + threshold) so the Mentor never speaks from a single data point. Read-only — never writes to the DB.…
onboarding-flow
Conversational protocol the Assistente follows to onboard the user — first message, iterative one-question-per-turn pacing, blocking checklist (the floor that unlocks the dashboard) vs rich checklist (what makes Writers actually useful), settore-agnostic question style (NEVER assume IT), and the mandatory checkpoint…
application-flow
DB + filesystem contract every Scrittore follows when taking a position from scored (≥50) to ready/excluded. Three gates BEFORE writing a single line of CV (anti-rewriting, anti-collision, link verification), one canonical path for deliverables, one final gate after the 3rd Critic round. Skipping any of these produces…
mentor-output
How the Mentor speaks once a pattern from mentor-patterns has crossed the threshold. Three output formats — strategic advice (rare, weighty), weekly digest, on-demand answer — each with strict shape and voice rules. The Mentor's authority comes from how rarely the words come and how heavy each one weighs; this skill…