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/jain777/jobclaw-skillsnpx agentmods add skills/jain777/jobclaw-skills/review-renderWrote 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/jain777/jobclaw-skills/review-render)<a href="https://agentmods.dev/skills/jain777/jobclaw-skills/review-render"><img src="https://agentmods.dev/badge/skills/jain777/jobclaw-skills/review-render/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/jain777/jobclaw-skills/review-render"><img src="https://agentmods.dev/badge/skills/jain777/jobclaw-skills/review-render.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 | $0.00071 | $0.01315 |
| Opus 5 | $0.00036 | $0.00658 |
| Sonnet 5 | $0.00014 | $0.00263 |
| Haiku 4.5 | $0.00007 | $0.00131 |
Grade A, and why
review-render 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 11d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-render
A rendered resume has defects that are invisible in the JSON and only show up on the page — a bullet wrapping with two dangling words, a half-empty page, content spilling one line onto page 2, an orphaned section header. This skill closes the loop the way a human does: make it, look at it, fix it, repeat — bounded so it always terminates.
Architecture split (see ../../_shared/RULES.md): rendercv renders; this skill (the brain) judges and decides the fix. Rendering levers live in render-resume; the visual judgment and content edits live here.
render-resume hands off to this skill as its mandatory final step (its §6 Self-QA) — so every resume is visually QA'd, not just ones where someone remembers to ask. You can also invoke it standalone on any existing rendered resume.
Inputs
- The JSON-Resume intermediate:
resumes/<name>.json(the editable source of content fixes). - The output PDF path:
resumes/<name>.pdf. - Optional: target
--max-pages,--theme(else frommeta.theme).
The loop (max 3 passes — never loop forever)
1. Render with page PNGs
python3 skills/render-resume/scripts/render.py \
--data resumes/<name>.json --out resumes/<name>.pdf --emit-png \
[--max-pages 1|2] [--theme T] [--date-col 3.3cm] [--density snug|compact|dense|tight]
This writes the PDF plus resumes/<name>.p1.png, .p2.png, ….
2. Deterministic gate (cheap — no vision tokens)
skills/render-resume/.venv/bin/python skills/render-resume/scripts/qa_report.py resumes/<name>.p*.png
Returns {pages, page_fills, last_page_fill, flags}. Flags: underfilled, sparse_last_page, overflow_risk.
3. Vision rubric — Read each .pN.png and score it against reference/rubric.md. Record each issue as {dimension, severity (critical/major/minor), where, suggested fix}.
4. Decide
- PASS when the deterministic
flagsare empty and the rubric has no critical/major issue (score ≥ 90). Report and stop. - Otherwise pick the single highest-severity issue, apply exactly one fix from the vocabulary below, and go back to step 1.
- After 3 passes, stop regardless; report the best version + any residual issues and a recommendation.
What ships with it
1 file 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.
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.
- 11d ago First seen · 78 lines · 71 tokens per session scan A e45d32752332
review-render is a skill published in the GitHub repository jain777/jobclaw-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 1,315 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
pdf-design
Designs PDF reports and proposals from HTML with previews and branding. Use to create, export, or securely upload a PDF.
document-design
Creates print-ready HTML that exports to PDF. Use to make a proposal, report, one-pager, newsletter, slides, or flyer.
solidworks-engineering-drawing
A SolidWorks skill for creating and reviewing engineering drawings, which are manufacturing documents showing views, measurements, holes, parts lists, and title-block information.
paperlab_book_typesetting_release
Final production review for PaperLab books across HTML, PDF, DOCX, and ODF. Use for responsive layout, page breaks, equation rendering, table overflow, caption style, running headers, figure placement, and release-candidate polish.
architectural-drawing-parser
Parse architectural drawings, floor plans, and building code compliance documents using Vision AI. Extracts building type, occupancy, floor areas, room layouts, dimensions, and code parameters. Use when: reading PDF floor plans, analyzing architectural drawings, extracting building data from images or scanned…
accessibility-pass
Use this skill whenever the user asks to check, review, or fix the accessibility of a PowerPoint deck, Word document, HTML page, or Markdown file, and before handing over any deck or document this agent just generated, so it does not ship with missing alt text, untitled slides, or unreadable colour contrast.