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/soheilfallah/jobxhunterWrote 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/soheilfallah/jobxhunter/cover-letter)<a href="https://agentmods.dev/commands/soheilfallah/jobxhunter/cover-letter"><img src="https://agentmods.dev/badge/commands/soheilfallah/jobxhunter/cover-letter/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/soheilfallah/jobxhunter/cover-letter"><img src="https://agentmods.dev/badge/commands/soheilfallah/jobxhunter/cover-letter.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 | $0.00015 | $0.00431 |
| Opus 5 | $0.00008 | $0.00216 |
| Sonnet 5 | $0.00003 | $0.00086 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
cover-letter 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 12d 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 COVER LETTER routine.
Draft first — never ask for a brain-dump. Write the letter complete from the JD + profile, name the employer in the body, and build the "why this employer" paragraph from the advert and verifiable public knowledge. If the user volunteers their own words (typed, or a voice-note transcript), treat them as source text and preserve their voice. Every factual claim maps to profile evidence. Deliver it finished — no placeholders, no "draft" label.
Follow SKILL.md ("Command: COVER LETTER").
Which reference each step reads. A step whose file is listed here is not finished until that file has been applied.
| Step | Read |
|---|---|
| Understand the role | references/jd-analysis.md |
| Openers, structure, evidence, etiquette | references/cover-letter.md |
| Voice pass, before returning | references/writing-voice.md — §"AI tells to strip" and §"Voice preservation"; the em-dash ban and the AI-vocabulary list are enforced here, not by taste |
| Humanizer pass (mandatory) | the installed humanizer skill, if present — apply its checklist to the whole letter. It supplements writing-voice.md, never replaces it. If it is not installed, writing-voice.md §"AI tells" is the whole pass; scripts/validate_profile.py WARNs on AI-tell vocabulary as the mechanical backstop |
| Academic / research targets | references/academic-register.md, on top of the above |
| Final scan | references/cv-mistakes.md §1 for buzzwords that leak from the CV into the letter |
| Market norms | references/uk-conventions.md (uk) · references/ca-conventions.md (ca) |
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.
- 12d ago First seen · 28 lines · 15 tokens per session scan A 4239c74fb277
cover-letter is a command published in the GitHub repository soheilfallah/jobxhunter (8 stars, last pushed 15d ago), licensed MIT. It adds 15 tokens to every session and 431 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
start
Onboard with Rebound — capture your base resume and build your private profile (skills, differentiators, and situation).
track
Record or update a job application in your local tracker so it shows on the Rebound dashboard.
match
Score how well roles fit you (50–90%+) and rank them — paste roles/URLs now; web-crawling discovery is on the roadmap.
profile
View or update your Rebound profile — skills, differentiators, and your private situation (work authorization, timeline).
rise
A supportive, practical check-in — momentum, next best action, and a plan that respects your runway. Knocked down, not out.
quick-eval
Quick job evaluation. Paste a JD and get a score plus one-paragraph summary. Faster than a full evaluate. Use when someone says 'quick eval', 'quick score', or 'just give me a number'.