Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/soheilfallah/jobxhunter/setupgit clone --depth 1 https://github.com/soheilfallah/jobxhunterWhat 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 | $0.00020 | $0.00414 |
| Opus 5 | $0.00010 | $0.00207 |
| Sonnet 5 | $0.00004 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Use the jobxhunter skill's SETUP routine.
Walk the user through SETUP.md, one step at a time, and verify each step before the next.
Keys are step 5 and optional — never lead with them, never block on them. Stop after the profile
is built and the user has looked at it; tell them which command to run next.
- Resolve or create the workspace (
python "${CLAUDE_PLUGIN_ROOT}/scripts/_lib.py" resolve; if none, scaffold withpython "${CLAUDE_PLUGIN_ROOT}/scripts/init_workspace.py" --workspace <dir> [--name <who>]). This drops the profile template, thedump/folder,WORKSPACE-MAP.md, and the tracker, then stops. - Onboard the connectors (only after the profile exists and the user said "now"): run
python "${CLAUDE_PLUGIN_ROOT}/scripts/setup_connectors.py" doctorfor a report of what's set vs missing, then follow the Agent script inreferences/tools-and-connectors.mdfor each missing one, in its order: Indeed first (built into claude.ai — Settings → Connectors → Indeed → Connect, no key), then Adzuna, Firecrawl, Reed, Dice optional. One connector per message; never block on a key; say what still works without it. Keys are the plugin's user-config values (/plugin configureorclaude plugin install … --config KEY=VALUE) — no manual JSON editing. Re-run the doctor after the user restarts Claude Code.
Follow SKILL.md ("Command: SETUP") and references/tools-and-connectors.md. Stop after setup so
nothing runs against an empty profile.
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.
- 3d ago First seen · 26 lines · 20 tokens per session scan A 3c5423c39a88
setup is a command published in the GitHub repository soheilfallah/jobxhunter (8 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 414 once invoked, about $0.0001 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 commands, from other repositories
track
Record or update a job application in your local tracker so it shows on the Rebound dashboard.
writing-coach
Human-voice writing coach — rewrite resumes and cover letters with brevity, burstiness, plain language, and authentic impact. Blocks AI-sounding prose.
tailor-resume
Tailor a resume to a job description, score it against ATS and HR rubrics, create a DOCX, and update the tracker.
triage-inbox
Sort application mail into the freehire tracker and drain the link queues.
start
Onboard with Rebound — capture your base resume and build your private profile (skills, differentiators, and situation).
dashboard
Launch the local Rebound dashboard (React) to visualize your job-search progress.