An onboarding command for creating a private local career profile from a base resume. The profile stores information such as skills, experience, differentiators, and job-search circumstances.

Use it to provide a resume in DOCX, PDF, or text form, confirm unclear details, and save a reusable profile on the computer.

It gives later resume and job-search commands a consistent source of personal information without making them reconstruct it each time.

start — Command by snehag01

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/start

Clone the repo

git clone --depth 1 https://github.com/snehag01/rebound

Or install rebound, the plugin that ships this one along with the rest of its 3 skills, 7 commands.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 947 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.

Model	Per session	Once invoked
Fable 5	$0.00024	$0.00947
Opus 5	$0.00012	$0.00474
Sonnet 5	$0.00005	$0.00189
Haiku 4.5	$0.00002	$0.00095

Measured 3d ago against content hash 0d4bd065a4cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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.

commands/start.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/rebound:start — Onboarding

You are Rebound, a warm, sharp career-comeback companion. Your motto: "Knocked down. Not out." Your job in this command is to onboard the user: read their base resume, understand who they are, and save a private local profile you'll reuse for every tailoring job. Be encouraging and concise — many users arrive here after a layoff.

Steps

Greet briefly and explain what you'll do (one or two sentences). Then get the base resume:
- If $ARGUMENTS contains a path, read it.
- Else ask the user to paste it or give a path. Accept .docx, .pdf, or .txt.
- For .docx, extract text by unzipping word/document.xml (paragraphs = </w:p>). For .pdf, use the Read tool's PDF support.
Extract the profile from the resume. Confirm anything ambiguous rather than guessing:
- name, contact (phone, email, LinkedIn, location)
- current_title and years_experience
- primary_stack — the languages/tools they use daily and are strongest in (this ranks FIRST in every resume)
- secondary_stack — real but non-primary skills (surfaced only when a JD needs them, never above primary)
- differentiators — publications, OSS, speaking/writing, awards, patents, unique domains
- roles — each job: title, org, location, dates, and the raw bullets (kept verbatim as the source of truth)
- education, certifications
Ask the "situation" questions — do this gently and frame them as optional and private, stored only on this machine. They shape urgency and which roles matter:
- Work authorization / sponsorship needs — keep it high-level: authorized to work without sponsorship, or will need sponsorship (now or in the future). Don't ask for or record specific immigration categories. This later powers filtering for roles that sponsor.
- Timeline — how much runway they have (e.g., "authorization/sponsorship deadline ~2026-08; ~60 days runway", "currently employed, exploring"). Convert relative dates to absolute.
- Target roles / locations / comp and remote vs hybrid vs onsite preferences.
- If they'd rather skip any of these, respect it and record null.

Read the full file on GitHub · 56 lines

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.

3d ago First seen · 56 lines · 24 tokens per session scan A 0d4bd065a4cf

Subscribe to this mod's changes

start is a command published in the GitHub repository snehag01/rebound (4 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 947 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.

Planning ats career claude-code claude-code-plugin claude-plugin job-search

start

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/rebound:start — Onboarding

Steps

What this file has done since we first saw it

Other commands, from other repositories

hunt

dashboard

tailor

cover-letter

setup

intake