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/tailor)<a href="https://agentmods.dev/commands/soheilfallah/jobxhunter/tailor"><img src="https://agentmods.dev/badge/commands/soheilfallah/jobxhunter/tailor.svg" alt="Measured on agentmods" 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 | $0.00642 |
| Opus 5 | $0.00008 | $0.00321 |
| Sonnet 5 | $0.00003 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
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 7d 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 TAILOR routine (its core) for a single job description.
Parse the JD → build the coverage matrix (strong / partial / adjacent-provisional / hard-gap) → select and
order real evidence → draft bullets (strong verb + real task + method + quantified outcome, anti-mirroring
guard) → voice pass + integrity checks (date / gap / profile check) → render an ATS-safe CV.docx + CV.txt
via scripts/render_docx.py → run the recruiter loop → file it. Respect the level (L0 / L1 default / L2).
Every build runs python scripts/validate_profile.py --profile <profile.md> --folder <dir> (exit 0
before rendering; exit 2 = the profile's rules block is broken — stop and report) and the mandatory
humanizer pass before anything is called ready.
Follow SKILL.md ("Command: TAILOR").
Which reference each step reads. Load only what the step needs; a step whose file is listed here is not finished until that file has been applied.
| Step | Read |
|---|---|
| 1. Parse the JD | references/jd-analysis.md |
| 2. Coverage matrix | references/tailoring-levels.md ("Gap classes"); for a career-change or non-linear story also references/career-narrative.md |
| 3. Select + order | references/keyword-taxonomy/<family>.md — as a palette to match real evidence, never a source of new skills |
| 4. Draft | references/cv-craft.md |
| 5. Voice pass | references/writing-voice.md (the de-slop + register model — never ship prose that has not been through it) and references/cv-mistakes.md §1 (banned buzzwords); then the installed humanizer skill, if present, on the summary and every bullet (mandatory when installed; validate_profile.py WARNs on AI-tell vocabulary as the mechanical backstop) |
| 5. Market conventions | pick by the profile's market: references/uk-conventions.md (uk) · references/ca-conventions.md (ca); academic/research targets also references/academic-register.md |
| 6. Render | references/ats-mechanics.md §9 — the ATS-safe checklist the render must satisfy |
| Recruiter loop | references/recruiter-rubric.md; the critic scores authenticity against references/writing-voice.md, the same standard the writer was held to |
| L2 only | references/tailoring-levels.md ("L2 — The alternative world"); the delta is mandatory |
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.
- 7d ago First seen · 33 lines · 15 tokens per session scan A d66580db1886
tailor is a command published in the GitHub repository soheilfallah/jobxhunter (8 stars, last pushed 11d ago), licensed MIT. It adds 15 tokens to every session and 642 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.
rise
A supportive, practical check-in — momentum, next best action, and a plan that respects your runway. Knocked down, not out.
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).
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'.