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-dashboardWrote 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-dashboard)<a href="https://agentmods.dev/skills/akbardevop/ai-job-agent/job-dashboard"><img src="https://agentmods.dev/badge/skills/akbardevop/ai-job-agent/job-dashboard/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-dashboard"><img src="https://agentmods.dev/badge/skills/akbardevop/ai-job-agent/job-dashboard.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 | $0.00127 | $0.00898 |
| Opus 5 | $0.00063 | $0.00449 |
| Sonnet 5 | $0.00025 | $0.00180 |
| Haiku 4.5 | $0.00013 | $0.00090 |
Grade A, and why
job-dashboard 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Dashboard
Thin wrapper around scripts/job-dashboard.mjs. Zero dependencies — pure Node with ANSI escape codes and Unicode box-drawing, so it works in any terminal.
Two modes:
| Mode | When to use |
|---|---|
| Snapshot (default) | Running inside Claude Code — prints a rich one-shot view in chat. Read-only, no TTY needed. |
Live TUI (live arg) |
User wants an interactive dashboard in their own terminal tab. You print the command, they run it outside Claude Code. |
Repo location
$AI_JOB_AGENT_ROOT → ~/.claude/skills/ai-job-agent/ → REPO_PATH marker file → ~/ai-job-agent/.
Workflow
Snapshot (default)
Run the script in snapshot mode and stream its output back to the user:
cd "$AI_JOB_AGENT_ROOT"
node scripts/job-dashboard.mjs --snapshot
The script outputs three sections:
- Applications — status breakdown (📄 applied · 📬 submitted · 💼 interview · 🎯 offer · ❌ rejected · 🚫 blocked · 🚪 withdrawn) + recent 15 rows from
application-tracker.csv. - Outreach — status breakdown + recent 15 cold emails from
outreach-log.csv. - Follow-ups — 🚨 overdue / ⏰ due / 👀 soon / 💤 waiting, sorted by urgency, showing who needs a nudge today.
Just print the script's output verbatim — it's already ANSI-colored with emoji and box-drawing chars. Don't re-render in markdown; the raw output IS the dashboard. (If the terminal strips ANSI for some reason, the box chars and emoji still carry the structure.)
If either CSV is missing, the script reports 0 rows and tells the user to run /job-setup first (which creates the trackers).
Live TUI ($ARGUMENTS = live)
Don't try to launch the TUI from inside Claude Code — the Bash tool doesn't have a TTY, so raw-mode keyboard input won't work. Instead, print the launch command and a short keybinding reference:
Run this in a separate terminal tab (inside this repo):
npm run dashboard
Keys once it's running:
tab / → / ← switch tab (Applications → Outreach → Follow-ups)
1 2 3 jump to tab
↑ ↓ j k scroll
r reload from disk
q esc ^C quit
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 · 74 lines · 127 tokens per session scan A 543daa87ad97
job-dashboard is a skill published in the GitHub repository AkbarDevop/ai-job-agent (54 stars, last pushed 4mo ago), licensed MIT. It adds 127 tokens to every session and 898 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 2026-08-30.
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…