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 tam159/next-role --skill resume-tailorgit clone --depth 1 https://github.com/tam159/next-roleWrote 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/tam159/next-role/resume-tailor)<a href="https://agentmods.dev/skills/tam159/next-role/resume-tailor"><img src="https://agentmods.dev/badge/skills/tam159/next-role/resume-tailor/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/tam159/next-role/resume-tailor"><img src="https://agentmods.dev/badge/skills/tam159/next-role/resume-tailor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.05810 |
| Opus 5 | $0.00036 | $0.02905 |
| Sonnet 5 | $0.00014 | $0.01162 |
| Haiku 4.5 | $0.00007 | $0.00581 |
Grade A, and why
resume-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume Tailor
Rewrite the candidate's resume to land an interview for one specific role at one specific company, using the hiring-recon report as the priority signal, then render it to a typeset PDF.
Inputs
The caller passes exact paths in the task description:
resume_path— the candidate's processed resume (markdown)jd_path— the processed job description (markdown)intake_path— optional intake notesresearch_path— the hiring-recon reportyaml_path— where to write the tailored resume YAML (must be under/tailored_resume/, ending.yaml)
Read all input files in full with read_file(path, limit=1000).
Workflow (3 steps, in order)
-
Decide theme and locale.
- If the user (in
intake_pathor the task description) explicitly named a built-in theme, honour it. Otherwise: scan the resume for engineering signals (engineer / developer / Python / SRE / MLOps / data / backend / frontend / DevOps / cloud architect / …). Engineering →engineeringclassic. Else →classic. - Detect resume language. If it matches a built-in locale, use it. If unsure or the language is not built-in, use
english.
- If the user (in
-
Write the YAML to
yaml_pathviawrite_file. Includecv:,design:(justtheme:), andlocale:(justlanguage:). Prepend a# changes:comment block summarising what you tailored. Do NOT write asettings:section — the next step injects it.Quoting rule (the #1 render-failure source): double-quote ANY string value that contains a colon followed by a space — headlines, summaries, highlights, titles, everywhere (
- "Strongest where AI meets execution: reusable patterns"). Unquoted, YAML silently parses the entry as a mapping and rendercv fails withInput should be a valid string. Same for strings ending in:and bare numbers (label: "2022",phone: "+15551234567"). When in doubt, quote — quoted strings are never wrong. -
Render & publish: call
render_resume_pdf(yaml_path)with the same backend path you wrote to in step 2. One call does the whole pipeline — it injects the canonicalsettings:block into an internal render copy (never into your YAML), runsrendercv render, and publishes<stem>.pdfnext to the YAML. Do NOT runrendercvviaexecuteand do NOT write asettings:block yourself. If the result starts withError (render):, read the rendercv output it contains, fix the YAML withedit_fileorwrite_file, then callrender_resume_pdf(yaml_path)again (idempotent — the PDF is overwritten).
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.
- 10d ago First seen · 250 lines · 72 tokens per session scan A 661becf32f9b
resume-tailor is a skill published in the GitHub repository tam159/next-role (50 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 5,810 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 2026-08-30.
Other skills, from other repositories
ocr
Extract text from images and scanned PDFs using local OCR (Tesseract). Keyless, offline. Use when asked to "read text from this image", "OCR this", "extract text from a screenshot/scan", or given an image with text.
paper-writing
Write and typeset formal documents — academic papers, reports, articles — using Markdown + Pandoc and LaTeX. Convert between formats (md↔pdf↔docx↔tex), manage citations with BibTeX/CSL. Keyless, local. Use when asked to "write a paper", "format this as LaTeX", "convert to PDF/Word", "add citations".
pdf-tools
Manipulate PDFs locally — merge, split, extract pages, rotate, compress, extract text, convert images↔PDF. Uses keyless local CLIs (pdftk/qpdf/pdftotext/poppler/img2pdf/Ghostscript). Use when asked to "merge PDFs", "split this PDF", "extract text from PDF", "compress PDF", "PDF to images".
critic-loop
Run the mandatory 3-round CV review loop with the Critico — autonomously, without going through the Capitano. For each round you spawn a FRESH CRITICO-S session (same N as your Scrittore session: SCRITTORE-2 → CRITICO-S2), send PDF + JD, wait for the structured verdict, kill the Critic, correct the CV, regenerate the…
parse-cv
Pre-process a CV/profile file (PDF, DOCX, ODT, RTF) into plain text BEFORE feeding it to the LLM context. Reduces token cost by 5-10x on long CVs and yields more reliable extraction than reading binary PDFs directly via multimodal vision. The Assistente calls this skill on every uploaded document in…
summarize
Quickly summarize articles, documents, URLs, long text, or multi-source content into concise key points. TRIGGER: "summarize", "summary", "tl;dr", "key points". NOT FOR: deep-research, consulting-report, narrative-writing use cases.