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 skills add Miracle-Aligner/job-search-hq --skill ingest-cvgit clone --depth 1 https://github.com/Miracle-Aligner/job-search-hqWrote 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/ingest-cv)<a href="https://agentmods.dev/skills/miracle-aligner/job-search-hq/ingest-cv"><img src="https://agentmods.dev/badge/skills/miracle-aligner/job-search-hq/ingest-cv/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/ingest-cv"><img src="https://agentmods.dev/badge/skills/miracle-aligner/job-search-hq/ingest-cv.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 | $0.00093 | $0.00510 |
| Opus 5 | $0.00046 | $0.00255 |
| Sonnet 5 | $0.00019 | $0.00102 |
| Haiku 4.5 | $0.00009 | $0.00051 |
Grade A, and why
ingest-cv 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
ingest-cv
Turn a real CV file into structured data the assessment skills can use.
Input
CV files live in profile/cv/ (gitignored; only .gitkeep + example-cv.md are tracked).
The user drops Backend-CV.pdf, Voice-CV.docx, etc. there. If the folder is empty, ask them
to add a file (or point you at a path) first.
Parse
- PDF → use the pdf skill to extract text (and OCR if scanned).
- DOCX → use the docx skill.
- Markdown / txt → read directly.
Extract: summary line, experience (company, title, dates, 2–4 impact bullets each), education, skills/stack, and anything that maps to a profile axis (years, seniority signals).
Link it
For each CV, add/update an entry in profile/profile.json cvVariants[]:
{ "key": "VOICE", "label": "ASR/TTS / voice-bot roles", "file": "profile/cv/Voice-CV.pdf" }
Keep a concise structured digest per variant (don't dump the whole CV) so assessment skills can
reference concrete evidence (projects, metrics) when scoring tech/level and when tailoring.
How assessment uses it
/add-vacancy and /cover-letter read profile/candidate.md and the CV digests to:
- score
tech/levelagainst real evidence, not just self-reported strengths; - pick the right CV
variantand propose concrete, evidence-backedchanges.
scripts/score.py stays pure rubric math — CV influence lives in the skill's judgement, not
the script.
Finish
Save profile/profile.json (gitignored). Confirm which variants are now available.
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 · 52 lines · 93 tokens per session scan A 3f54c6c5486c
ingest-cv is a skill published in the GitHub repository Miracle-Aligner/job-search-hq (1 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 510 once invoked, about $0.0005 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
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.
scan-inbox
Classify unscanned mailbox messages, fuzzy-match each to an existing application, and write the proposal back. The user approves in /inbox.
resume-campaign
Resume a paused JobPilot campaign by id. Re-flips the campaign to inprogress and replays the apply loop on any remaining approved jobs without re-asking for fit confirmation.
resume-tailoring
Methodology for tailoring a resume to a job description honestly and effectively — fit analysis, gap handling, keyword mirroring, fast-learner framing, and primary-over-secondary emphasis. Use whenever curating or rewriting a resume for a specific role.
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.