Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Miracle-Aligner/job-search-hqnpx agentmods add skills/miracle-aligner/job-search-hq/cover-letterWrote 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/skills/miracle-aligner/job-search-hq/cover-letter)<a href="https://agentmods.dev/skills/miracle-aligner/job-search-hq/cover-letter"><img src="https://agentmods.dev/badge/skills/miracle-aligner/job-search-hq/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/skills/miracle-aligner/job-search-hq/cover-letter"><img src="https://agentmods.dev/badge/skills/miracle-aligner/job-search-hq/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 | $0.00082 | $0.00518 |
| Opus 5 | $0.00041 | $0.00259 |
| Sonnet 5 | $0.00016 | $0.00104 |
| Haiku 4.5 | $0.00008 | $0.00052 |
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
cover-letter
Replace the old DOU "note" with a real, tailored cover letter. Writes the coverLetter field
on one vacancy in data/vacancies.json.
Inputs
- The vacancy — role, JD recap,
plus/minus,summary, company. profile/candidate.md+ CV digests — the candidate's voice and concrete evidence.- Ask the user for length/format if it matters (DOU "about you" blurb ≈ 4–6 sentences; a full letter ≈ 3 short paragraphs). Default to the short blurb.
Write it like a human
- Specific, not generic. Name the actual product/problem and one concrete reason the candidate fits (a real project or result from the CV). A reader should be unable to paste it into another application unchanged.
- No AI tells / clichés. Ban: "I am excited to apply", "passion for", "leverage", "synergy", "fast-paced environment", "wear many hats", "I believe I would be a great fit", em-dash-stuffing, triads-of-three everywhere. Plain, direct sentences.
- Honest. Don't claim experience the profile says is a gap. Lead with real overlap.
- The candidate's register — match the tone in
profile/candidate.md/ their CV; not corporate. - Open with the hook (why this role), middle with one piece of proof, close with a light, non-grovelling sign-off.
Show the draft, take one round of edits, then save.
Persist
Write to vacancies[i].coverLetter (markdown/plain text). The viewer shows it in a "Cover letter"
card with copy-to-clipboard. (Legacy note is still read by the viewer, but write coverLetter.)
Finish
python3 scripts/validate.py
python3 scripts/build.py --real
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 · 48 lines · 82 tokens per session scan A e899bc8dcf39
cover-letter is a skill published in the GitHub repository Miracle-Aligner/job-search-hq (1 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 518 once invoked, about $0.0004 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 skills, from other repositories
tailor-resume
Choose the best existing resume base/variant for a job, or create a new tailored variant when nothing fits.
tanstack-form-composition
Migrate a React @tanstack/react-form codebase from the prop-drilled useForm + erased-form-type pattern to the official createFormHook composition API (useAppForm / withForm / field.X). Use when a project threads a form object (often cast to an any-erased type like ReactFormExtendedApi ) through field-wrapper…
apply
Apply to a single job (URL or pasted page) with fit review, or score and apply the job links pasted into an apply campaign when no argument is given.
auto-apply
Search a job board and autonomously apply to matching jobs one at a time, until paused, exhausted, or the max-applications cap is hit.
teaser-video
Film, cut, and deliver a short teaser/demo video of any app by driving it with Playwright and editing with ffmpeg - storyboard, authenticated capture, PII review, animated title cards, MP4 + GIF. Use for "make a teaser", "record a demo video", "product launch video", "screen recording for the README".
networking
Find a hiring manager/recruiter for a role (or company) and send a personalized message via cold email or LinkedIn, with per-campaign channels and autonomy.