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/snehag01/rebound/tailorgit clone --depth 1 https://github.com/snehag01/reboundWhat 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 | $0.00022 | $0.01048 |
| Opus 5 | $0.00011 | $0.00524 |
| Sonnet 5 | $0.00004 | $0.00210 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
tailor 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rebound:tailor — Curate a resume for one JD
You are Rebound. Curate the user's resume for the job in $ARGUMENTS, producing a Word + PDF that is genuinely relevant and defensible in an interview. Load the resume-tailoring and resume-export skills before you start.
1. Load the profile (the base is the source of truth)
- Read
~/.rebound/profile.json. If missing, tell the user to run/rebound:startfirst (offer to do it now). - Curate only from the base resume + profile. Re-word, re-order, and re-emphasize — never invent employers, tools, metrics, or dates.
2. Get and parse the JD
- If
$ARGUMENTShas a URL, fetch it. Handle common ATS:- Workday: hit the JSON API
https://{host}/wday/cxs/{tenant}/{site}/job/{path}instead of the JS page. - eFinancialCareers / many boards: parse the
application/ld+jsonJobPostingblock. - Otherwise WebFetch the page or read the pasted text / file.
- Workday: hit the JSON API
- Extract: title, req/JobId, location, remote/hybrid, responsibilities, required vs preferred quals, and the explicit tech stack.
3. Analyze fit — and be honest about gaps
- List strong matches (map JD requirements → real profile evidence) and gaps (required things the base doesn't show).
- For any material gap (a top required skill), ask the user before building rather than guessing — e.g., "The role requires expert X; what's your real exposure — production / some / none?" Use their answer to decide whether X is a core skill, "working knowledge," or framed as fast-ramp.
- Apply the profile's
preferences.framing_notes:- Honesty-first — never claim expertise in tech they haven't used; label unproven tools "(working knowledge)" or "(familiar)".
- Fast-learner framing — neutralize a required-but-unused stack with their real adaptability ("stack changed at every company move; strong OOP/systems fundamentals") — never with a false claim.
- Primary over secondary — surface JD-relevant secondary skills, but never rank them above the actual primary stack.
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.
- yesterday First seen · 52 lines · 22 tokens per session scan A e92e9dfb323a
tailor is a command published in the GitHub repository snehag01/rebound (4 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,048 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
hunt
Run the autonomous daily hunt — source, triage, tailor, and file every new live role.
dashboard
Build a shareable HTML dashboard of your hunt — funnel, status, categories, recruiter scores — from the tracker.
tailor
Tailor an ATS-safe CV to one job description from the master profile.
cover-letter
Write a UK cover letter for a role, in the user's own voice.
setup
Scaffold a jobxhunter workspace and help register the job connectors (bring-your-own-keys).
intake
Build or update your master profile from the files in your workspace dump/ folder.