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/Light0305/Light-skillsnpx agentmods add skills/light0305/light-skills/light-typesettingWrote 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/light0305/light-skills/light-typesetting)<a href="https://agentmods.dev/skills/light0305/light-skills/light-typesetting"><img src="https://agentmods.dev/badge/skills/light0305/light-skills/light-typesetting.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 | $0.00169 | $0.02938 |
| Opus 5 | $0.00084 | $0.01469 |
| Sonnet 5 | $0.00034 | $0.00588 |
| Haiku 4.5 | $0.00017 | $0.00294 |
Grade A, and why
light-typesetting 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 7d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Typesetting · stage 11
Turn approved author artifacts into a reproducible PDF submission bundle. The job is not merely to make LaTeX compile: preserve provenance, select a coherent engine/backend, preflight dependencies, compile to convergence, locate the first root cause, run profile-driven desk-reject checks, and hand exact PDF/page facts to venue-matching.
Read typesetting-resource-map.md before running a real build. Read
references/build_contract.md before writing or consuming machine artifacts.
Use references/latex_errors.md only after the first source-located error is
known. Use a venue template under templates/ only when it matches the current
author kit; the bundled copy is a starting point, not current venue truth.
Non-negotiable boundaries
- Consume citation
delivery.json,references.bibandcitekey-audit.json. Requiredelivery.status=DELIVERED, declareddeliverable_hashes, empty citation failures and empty claim-review leftovers. Declared citation deliverables must be relative paths inside the citation delivery directory, and the build snapshot must preserve the audit, failure and claim-review sidecars under provenance. Check staged keys and compilation. Do not re-decide DOI existence, metadata conflicts, retractions or claim relevance. - Consume figure files, declared dimensions/DPI and source manifest. Require
the manifest to be
light.figure_delivery.v1orlight.figure_build.v1and require the embedded file hash to match a declared output hash. For empirical figure deliveries, require confirmed result-analysis evidence binding. Check presence, embedding, float/layout and compilation. Do not redo visual honesty, scientific content or publication-size generation. - Consume the approved paper-writing manuscript. Do not invent claims, references, experiments or numbers to close a page budget.
- Take page, anonymity, template, font and page-box rules only from user input or current authoritative instructions with URL/date provenance. Never embed a universal venue limit.
- Keep tool/resource failure as
UNAVAILABLE. Never call it manuscriptERROR, never call itPASS, and never mark the deliveryDELIVERED. - Keep stage-11 critical scope to typesetting. Security/network/tool
unavailability does not enlarge it.
ROUTEShas no key 11; repair failures inside stage 11 and never invent a back-edge.
What ships with it
17 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.md 6.6 KB
- references/build_contract.md 4.7 KB
- references/latex_errors.md 3.9 KB
- scripts/build_submission.py 52 KB runs code
- scripts/compile_driver.py 21 KB runs code
- scripts/desk_reject_gate.py 32 KB runs code
- scripts/precheck_log.py 11 KB runs code
- scripts/submission_check.py 16 KB runs code
- scripts/submission_readiness.py 17 KB runs code
- templates/acm_sigconf.tex 2.6 KB
- templates/ctex_chinese.tex 2.1 KB
- templates/elsevier_elsarticle.tex 2.0 KB
- templates/ieee_bare_conf.tex 2.5 KB
- templates/springer_llncs.tex 1.9 KB
- templates/submission-readiness.example.json 1.9 KB
- templates/typesetting_input.json 1.3 KB
- typesetting-resource-map.md 5.9 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.
- 7d ago First seen · 276 lines · 169 tokens per session scan A 8093998522b2
light-typesetting is a skill published in the GitHub repository Light0305/Light-skills (598 stars, last pushed 2mo ago), licensed MIT. It adds 169 tokens to every session and 2,938 once invoked, about $0.0008 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
figure-drawing
MANDATORY skill for creating any figure, diagram, chart, table visualization, or TikZ graphic in a paper. Must be activated BEFORE writing any drawing code. Produces standalone .tex → compiled PDF/PNG → \includegraphics in paper. Never inline TikZ code directly into paper sections.
academic-latex-layout
Use when working on academic paper LaTeX layout, figure/table float placement, draft-to-template LaTeX generation, existing .tex project layout repair, figures piling up, figures far from text, large blank areas, two-column figure/table placement, page-limit layout cleanup, or compiled PDF layout review.
tikz-figure-review
Review and fix alignment, label collision, clipping, legend-over-data, overlap, and layout issues in TikZ and pgfplots figures inside LaTeX documents. Use when the user wants to review figures in a paper, tutorial, lecture notes, or thesis before submission; when a reviewer flags figure problems; when a rendered…
ieee-latex
Compile, diagnose, and fix IEEEtran LaTeX manuscripts for JSAC, TWC, TCOM, WCL, CL, and related IEEE journals: documentclass options, BibTeX/IEEEtran bibliography, undefined citations/refs, overfull hboxes, figure/table placement, algorithm/equation numbering, Index Terms, EDICS, biographies, and final PDF checks. Use…
awesome-ieee-report
Generates IEEE-format LaTeX technical reports from project requirements and codebase evidence, using academic prose, pseudocode-only explanations, BibTeX references, and IEEEtran formatting.
autoreport
Use when generating a physics or engineering experiment report from measured data and reference materials — orchestrates Theory, Data Analysis, Plotting, and Report sub-agents to produce a compiled LaTeX PDF. Also use for any sub-task in that pipeline: deriving formulas, analyzing lab data, plotting measurements with…