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 CloudWave818/ieee-skills --skill ieee-latexgit clone --depth 1 https://github.com/CloudWave818/ieee-skillsWrote 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/cloudwave818/ieee-skills/ieee-latex)<a href="https://agentmods.dev/skills/cloudwave818/ieee-skills/ieee-latex"><img src="https://agentmods.dev/badge/skills/cloudwave818/ieee-skills/ieee-latex/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/cloudwave818/ieee-skills/ieee-latex"><img src="https://agentmods.dev/badge/skills/cloudwave818/ieee-skills/ieee-latex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 24 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00086 | $0.00460 |
| Opus 5.5 | $0.00034 | $0.00184 |
| Sonnet 5.5 | $0.00017 | $0.00092 |
| Haiku 4.5 | $0.00009 | $0.00046 |
Grade A, and why
ieee-latex 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 2mo 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.
What it actually says
IEEE LaTeX Router
Use this skill to fix IEEE LaTeX issues while preserving manuscript content and target-template compliance.
Do not make broad package or template changes unless necessary. Follow the routing protocol and load the selected fragments.
Routing Protocol
- Read
manifest.yaml. - Read every file listed under
always_load. - Detect the axes:
task_type: compile-debug / layout-fix / float-placement / table-formatting / equation-formatting / algorithm-formatting / bibliography / pdf-check.venue_type: transaction / journal / letter / conference / magazine / generic.object_type: figure / table / equation / algorithm / reference / class-file / whole-manuscript.failure_mode: overfull-hbox / float-too-large / figure-at-end / broken-citation / duplicate-label / package-conflict / unreadable-table / sparse-page.stage: drafting / pre-submission / revision / final-production.
- State the detected axes when useful.
- Load only the matching fragments.
- Inspect source, log, and rendered output when available. Do not judge final layout from
.texalone when a PDF can be rendered or inspected. - Apply the smallest IEEE-compatible fix.
Output Contract
Diagnosis:
- Cause:
- Affected object:
Fix:
[minimal LaTeX change or instructions]
Why this works:
[short explanation]
Follow-up checks:
- [compile/render/check PDF]
For direct code edits, preserve author content and change only the necessary LaTeX structure.
Red Lines
Do not switch away from the target IEEE template for convenience.
Do not break IEEE bibliography style for cosmetic citation output.
Do not use screenshots for plots when vector or high-resolution exports are possible.
What ships with it
38 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.
- agents/openai.yaml 195 B
- manifest.yaml 3.5 KB
- static/core/output-format.md 306 B
- static/core/stance.md 322 B
- static/core/workflow.md 444 B
- static/fragments/failure_mode/broken-citation.md 190 B
- static/fragments/failure_mode/duplicate-label.md 157 B
- static/fragments/failure_mode/figure-at-end.md 261 B
- static/fragments/failure_mode/float-too-large.md 169 B
- static/fragments/failure_mode/overfull-hbox.md 270 B
- static/fragments/failure_mode/package-conflict.md 196 B
- static/fragments/failure_mode/sparse-page.md 210 B
- static/fragments/failure_mode/unreadable-table.md 200 B
- static/fragments/object_type/algorithm.md 120 B
- static/fragments/object_type/class-file.md 127 B
- static/fragments/object_type/equation.md 153 B
- static/fragments/object_type/figure.md 163 B
- static/fragments/object_type/reference.md 108 B
- static/fragments/object_type/table.md 166 B
- static/fragments/object_type/whole-manuscript.md 169 B
- static/fragments/stage/drafting.md 124 B
- static/fragments/stage/final-production.md 140 B
- static/fragments/stage/pre-submission.md 201 B
- static/fragments/stage/revision.md 123 B
- static/fragments/task_type/algorithm-formatting.md 219 B
- static/fragments/task_type/bibliography.md 225 B
- static/fragments/task_type/compile-debug.md 312 B
- static/fragments/task_type/equation-formatting.md 199 B
- static/fragments/task_type/float-placement.md 215 B
- static/fragments/task_type/layout-fix.md 187 B
- static/fragments/task_type/pdf-check.md 229 B
- static/fragments/task_type/table-formatting.md 308 B
- static/fragments/venue_type/conference.md 143 B
- static/fragments/venue_type/generic.md 119 B
- static/fragments/venue_type/journal.md 161 B
- static/fragments/venue_type/letter.md 124 B
- static/fragments/venue_type/magazine.md 171 B
- static/fragments/venue_type/transaction.md 164 B
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.
- 2mo ago First seen · 53 lines · 86 tokens per session scan A d4f631e1d6c9
ieee-latex is a skill published in the GitHub repository CloudWave818/ieee-skills (429 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 460 once invoked, about $0.0003 per session on Opus 5.5. 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.
ieee-latex compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ieee-latexCloudWave818/ieee-skills | Skill | 429 | 2mo ago | MIT | A | 86 | Codex |
| pydicomK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 52 | Claude Code, Codex |
| nature-paper2wordYuan1z0825/nature-skills | Skill | 52k | 2d ago | Apache-2.0 | A | 233 | Codex |
| pptx-postersK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 59 | Claude Code |
| nature-paper-transYuan1z0825/nature-skills | Skill | 52k | 2d ago | Apache-2.0 | A | 68 | Codex |
| extracting-lab-tablesmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 210 | Claude Code |
| paper-compilewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | B | 53 | Claude Code |