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/larsboes/axon/cv-buildernpx skills add larsboes/Axon --skill cv-buildergit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/cv-builder)<a href="https://agentmods.dev/skills/larsboes/axon/cv-builder"><img src="https://agentmods.dev/badge/skills/larsboes/axon/cv-builder.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 | $0.00117 | $0.01248 |
| Opus 5 | $0.00059 | $0.00624 |
| Sonnet 5 | $0.00023 | $0.00250 |
| Haiku 4.5 | $0.00012 | $0.00125 |
Grade A, and why
cv-builder 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CV Builder
Drive the CV through $CV — the source of truth; this skill is the runbook. No content
generation here: every build is a deterministic filter over the master file, never a rewrite.
This setup is not hardcoded. The actual CV content (name, employer, contact info) lives in
$AXON_PERSONAL_ROOT/data/cv/master_cv.yaml, never in this skill or in Axon. If that file is
missing, stop and tell the user to copy capabilities/cv/master_cv.schema.yaml there and fill
it in — do not draft CV content yourself.
Variables
| var | value | notes |
|---|---|---|
$CV |
capabilities/cv/cv |
launcher, relative to $AXON_ROOT |
$MASTER |
$AXON_PERSONAL_ROOT/data/cv/master_cv.yaml |
the one file to maintain; $CV refuses to run without it |
$PROFILE |
one of $CV list-profiles' output |
e.g. swe, quant, consulting, general |
$LANG |
en or de |
defaults to en if the user doesn't say |
Workflow
$CV list-profiles— read the actual tags currently defined (don't assume the list from memory; it's just data and changes as the master file changes).- Match the user's ask to the closest tag:
- A job posting/description or a stated role type ("SWE role", "consulting") → pick the closest existing tag from step 1's output.
- Ambiguous, or nothing close enough → ask the user to pick from the actual list rather than guessing.
- Pick
$LANGfrom what the user said (German posting/company →de; otherwiseenunless told). $CV build --profile $PROFILE --lang $LANG→ report the printed output path back to the user. Building every profile/lang at once:$CV build --all(optionally--all --lang deto restrict to one language). Iterating on the master file rather than producing one PDF:$CV watch --profile $PROFILE --lang $LANGrecompiles on every save. Tell the user to open the PDF in a viewer that reloads on change (Preview, Skim, a browser tab) —watchblocks until they stop it.- Never edit
$MASTERon the user's behalf mid-conversation to "tailor" wording for a specific posting — that recreates the AI-tailoring flow this design deliberately left out. If the user wants new content, tell them to add it (with the rightprofiles:tags) to the master file themselves.
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 · 75 lines · 117 tokens per session scan A e240da6ed9e1
cv-builder is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed 3d ago), licensed MIT. It adds 117 tokens to every session and 1,248 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
invoice
A printable invoice page — sender + recipient block, line items table, tax breakdown, totals, and payment instructions. Use when the brief mentions "invoice", "bill", "billing statement", or "发票".
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI.
ai-legal-document-generation
AI legal document generation powered by CellCog. Contracts, NDAs, terms of service, privacy policies, freelance agreements, employment contracts, compliance reviews, legal research. Precision legal drafting from natural language prompts. Not legal advice.
doc-processor
当用户要生成 Word/Excel/PowerPoint、做文档格式转换（Markdown ↔ HTML ↔ DOCX ↔ PDF）、PDF 文本提取、读写 Excel、合并文档或批量转换时使用。.
Use whenever the user works with PDF files — reading/extracting text from PDFs (lecture notes, textbook chapters, HW problems, HW solutions, hand-written answers), converting PDFs to markdown for downstream analysis, merging/splitting PDFs, or creating PDFs. For scanned or hand-written PDFs, OCR is required…
wes-clinical-report-en
Generates professional clinical PDF reports in English from WES (Whole Exome Sequencing) data with clinical interpretation summary, pharmacogenomic alerts, and follow-up recommendations.