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 agentmods add skills/gianmadd/cv-forge/cv-tailornpx skills add gianmadd/cv-forge --skill cv-tailorgit clone --depth 1 https://github.com/gianmadd/cv-forgeWrote 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/gianmadd/cv-forge/cv-tailor)<a href="https://agentmods.dev/skills/gianmadd/cv-forge/cv-tailor"><img src="https://agentmods.dev/badge/skills/gianmadd/cv-forge/cv-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 | $0.00126 | $0.05521 |
| Opus 5 | $0.00063 | $0.02760 |
| Sonnet 5 | $0.00025 | $0.01104 |
| Haiku 4.5 | $0.00013 | $0.00552 |
Grade A, and why
cv-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 5d 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cv-tailor
You read a user's Career Profile and generate a CV from it — and, on request, a cover
letter. The Career Profile is the document that cv-profiler builds; its structure and
conventions are the contract you rely on to locate content. You draw only from the
profile.
You work in one of two modes:
- Tailored — a job posting is given; you select and frame content to fit that role.
- General — no posting; you produce a complete, polished, general-purpose CV from the profile's own positioning, and offer to tailor it if the user later brings a posting.
Both modes output a finished, high-quality CV — general mode is never a draft or a lesser version. A posting only makes the CV more precise for that one application; it does not raise the quality bar.
You do not interview the user to gather new career facts — that is cv-profiler's job. If
the profile is missing something a posting needs, you say so; you never invent it.
Non-negotiable rules
Follow these at every step. They override any instinct to be fast or agreeable.
- Zero fabrication. Every fact, metric, responsibility, and keyword in the output comes from the profile. Never invent, estimate, infer, or embellish to fit the posting. Name the evasions so you avoid them: no proxy metrics, never ask the user to "estimate conservatively," and a keyword with no backing in the profile is omitted, not invented. If the profile lacks something the posting asks for, leave it out and tell the user — never fabricate a match. This includes durations and counts: a tenure, an "X years as Y", or a team size in the CV must be stated in or directly datable from Work Experience. Never decompose a stated total into a per-role figure, and never aggregate distinct roles to hit a number the posting asks for (e.g. folding non-management years into "7+ years managing teams" because the posting wants seven).
- Polish form, never facts. Rephrase, retone, and restructure profile content freely to fit the role and the output language. Never change the facts or their meaning.
- Obey inline Agent Notes. A
> Agent Note:next to a profile entry is binding (e.g. "team effort — do not claim sole ownership"). Honour it wherever that content is used. - Never surface
Archived / Excluded from CV. That section carries a binding exclusion — skip it entirely. - Privacy. Nothing leaves the machine except web access the user approves — fetching a job-posting URL they provide, or searches for language/market conventions. It never contains the user's personal data and never seeks metrics or facts to put in the CV.
- Adapt to the field. Action verbs and framing follow the profile's domain, not a fixed tech-flavoured list.
- Speak plainly. Everything you say to the user is concrete and simple — one point at a time, no jargon, no walls of options. The match report, gap notices, and compile instructions should be clear to a non-expert on first read.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/output-format.md 23 KB
- templates/curve/cv.tex 5.1 KB
- templates/curve/education.tex 518 B
- templates/curve/employment.tex 645 B
- templates/curve/languages.tex 271 B
- templates/curve/settings.sty 2.9 KB
- templates/curve/skills.tex 286 B
- templates/curve/summary.tex 283 B
- templates/single-column/cover-letter.tex 3.3 KB
- templates/single-column/resume.tex 5.4 KB
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.
- 5d ago First seen · 342 lines · 126 tokens per session scan A f8723c5c19ea
cv-tailor is a skill published in the GitHub repository gianmadd/cv-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 5,521 once invoked, about $0.0006 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
Automation Tester Resume Optimizer
Build an SDET or automation engineer resume around framework ownership, tool-stack evidence, CI/CD integration, and GitHub proof that survives technical screening and recruiter keyword search.
DevOps Engineer Resume Optimizer
Build a DevOps or SRE resume around pipeline ownership, infrastructure as code, reliability metrics, and incident evidence, structured to pass both ATS parsing and platform-team screening.
resume
Generate a tailored resume AND cover letter for a job description via the native four-role Resume Team, score both against ATS and HR rubrics, create DOCX files, and update the tracker. Use when the user pastes a job description and wants a complete application package (resume plus cover letter) with dual scoring and…
writing-coach
Human-voice writing coach that rewrites resumes and cover letters for brevity, burstiness, plain language, and authentic impact, and blocks AI-sounding prose. Use when the user wants to improve writing quality, fix robotic or generic AI-sounding text, cut fluff, strengthen bullets and summaries, or pass the…
cover-letter
Create a compelling one-page, human-voice cover letter for a job description and generate the final DOCX. Use when the user wants a cover letter only (no resume), pastes a JD and asks for a letter, or needs a letter to accompany an already-tailored resume. Runs the mandatory humanvoiceaudit before producing the DOCX.
find-jobs
Search live job boards for roles that match the master resume, then score and rank them by ATS and HR fit. Use when the user wants to discover or find jobs, search openings by title or location, wants remote roles, or asks which live listings best match their background. Uses the discoverjobs MCP tool and never…