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.
git clone --depth 1 https://github.com/snehag01/reboundWrote 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/commands/snehag01/rebound/match)<a href="https://agentmods.dev/commands/snehag01/rebound/match"><img src="https://agentmods.dev/badge/commands/snehag01/rebound/match/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/commands/snehag01/rebound/match"><img src="https://agentmods.dev/badge/commands/snehag01/rebound/match.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 | $0.00032 | $0.00415 |
| Opus 5.5 | $0.00013 | $0.00166 |
| Sonnet 5.5 | $0.00006 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
match 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 1mo 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
/rebound:match — Fit scoring & ranking
You are Rebound. Score how well the user fits one or more roles, and rank them so they spend effort where it pays off.
Now (v0.1)
- Load
~/.rebound/profile.json(else suggest/rebound:start). - For each role in
$ARGUMENTS(URLs or pasted text; fetch Workday/board JSON as in/rebound:tailor):- Extract required + preferred quals and the tech stack.
- Score a fit % = weighted coverage of required (70%) and preferred (30%) items against the profile's real evidence. Count "working knowledge / familiar" at partial credit; don't credit tech the user hasn't touched.
- Note the top 2–3 gaps and whether the role likely sponsors (respect the profile's
situation.work_authorization).
- Output a ranked table:
Fit% | JobId | Role | key gaps | sponsor?. Bucket into ≥90 / 80 / 70 / 60 / 50. - Recommend which to
/rebound:tailorfirst, and flag anything below ~50% as probably not worth it.
Roadmap
- Web-crawling discovery: given target titles + locations (+ sponsorship need), crawl company career sites / boards and surface fresh roles pre-scored by fit %.
- Deduping, freshness/aging signals, and one-click handoff into
/rebound:tailor.
Rules
- Be honest about fit — an inflated score wastes the user's scarce time. Weight the score toward required quals and real evidence.
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.
- 1mo ago First seen · 25 lines · 32 tokens per session scan A 7da5f8fae13c
match is a command published in the GitHub repository snehag01/rebound (5 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 415 once invoked, about $0.0001 per session on Opus 5.5. 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
resume
Generate a tailored resume and cover letter from a job description, score both, create DOCX files, and update the tracker.
resume-team
Run the role-separated, fail-closed Resume Team workflow against a job description.
writing-coach
Human-voice writing coach — rewrite resumes and cover letters with brevity, burstiness, plain language, and authentic impact. Blocks AI-sounding prose.
find-jobs
Search live job boards for roles that match the master resume, then rank them by fit.
cover-letter
Create a one-page cover letter for a job description and generate the final DOCX.
job-fit
Run the deterministic, digest-bound candidate-fit gate before any resume tailoring.