agentmods.dev

track

A command for recording or updating job applications in a local tracker used by the Rebound dashboard.

In plain words
What is it for?
Use it to add applications, update statuses such as applied or offer, and store details such as company, role, location, fit, sponsorship, dates, and resume file.
Why use it?
It keeps application details and progress in one place instead of relying on scattered notes.

Command

4 1mo ago A scan 19 tokens original MIT
View the source file snehag01/rebound
Install

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.

agentmods
npx agentmods add commands/snehag01/rebound/track
Clone the repo
git clone --depth 1 https://github.com/snehag01/rebound
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 482 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00482
Opus 5 $0.00010 $0.00241
Sonnet 5 $0.00004 $0.00096
Haiku 4.5 $0.00002 $0.00048

Measured yesterday against content hash 41488c5042d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

track 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 yesterday.

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.

commands/track.md · 37 lines

What it actually says

/rebound:track — Log an application

You are Rebound. Maintain the local datastore the dashboard reads: ~/.rebound/data/tracker.json (create it and ~/.rebound/data/ if missing).

Datastore shape

{
  "client": {"name": "", "title": "", "updated": "YYYY-MM-DD"},
  "goals": {"weekly_target": 8},
  "applications": [
    {"id": "", "company": "", "role": "", "location": "",
     "status": "curated|applied|screen|onsite|offer|accepted|rejected",
     "fit": 0, "sponsor": false, "resume_file": "",
     "applied_date": null, "updated_date": "YYYY-MM-DD", "source": "", "notes": ""}
  ]
}

What to do

  • Parse $ARGUMENTS (natural language is fine) into one or more application records.
  • add: append a new record. Pull defaults from context — if you just ran /rebound:tailor, reuse that JobId, company, role, fit, sponsor flag, and the exact resume_file you produced.
  • update: find the record by id (or company+role) and change fields — most often status as the person moves curated → applied → screen → onsite → offer.
  • Always set updated_date to today; set applied_date when status first becomes applied.
  • Keep client.name/title in sync with ~/.rebound/profile.json; refresh client.updated.
  • Write valid JSON back (pretty-printed). Confirm the change and show the new headline counts (curated, applied, interviews, offers).

Rules

  • Local only — never send this anywhere.
  • Don't store the private situation here; that lives in profile.json and is never rendered on the dashboard.
  • After changes, remind the user they can view it with /rebound:dashboard.
Changes

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.

  1. yesterday First seen · 37 lines · 19 tokens per session scan A 41488c5042d9

Subscribe to this mod's changes

track is a command published in the GitHub repository snehag01/rebound (4 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 482 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.

Analytics and metricsResearchatscareerclaude-codeclaude-code-pluginclaude-pluginjob-search
Related

Other commands, from other repositories

hunt

Run the autonomous daily hunt — source, triage, tailor, and file every new live role.

soheilfallah/jobxhunter · 20 tokens

dashboard

Build a shareable HTML dashboard of your hunt — funnel, status, categories, recruiter scores — from the tracker.

soheilfallah/jobxhunter · 23 tokens

tailor

Tailor an ATS-safe CV to one job description from the master profile.

soheilfallah/jobxhunter · 15 tokens

cover-letter

Write a UK cover letter for a role, in the user's own voice.

soheilfallah/jobxhunter · 15 tokens

setup

Scaffold a jobxhunter workspace and help register the job connectors (bring-your-own-keys).

soheilfallah/jobxhunter · 20 tokens

intake

Build or update your master profile from the files in your workspace dump/ folder.

soheilfallah/jobxhunter · 16 tokens