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-paper-readergit 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-paper-reader)<a href="https://agentmods.dev/skills/cloudwave818/ieee-skills/ieee-paper-reader"><img src="https://agentmods.dev/badge/skills/cloudwave818/ieee-skills/ieee-paper-reader/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-paper-reader"><img src="https://agentmods.dev/badge/skills/cloudwave818/ieee-skills/ieee-paper-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.00476 |
| Opus 5.5 | $0.00032 | $0.00190 |
| Sonnet 5.5 | $0.00016 | $0.00095 |
| Haiku 4.5 | $0.00008 | $0.00048 |
Grade A, and why
ieee-paper-reader 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 Paper Reader Router
Use this skill to turn an IEEE paper into a structured technical brief. Focus on contribution logic, method mechanics, evidence, and reuse value.
Do not provide only a generic summary. Follow the routing protocol and load the selected fragments.
Routing Protocol
- Read
manifest.yaml. - Read every file listed under
always_load. - Detect the axes:
reading_purpose: literature-review / implementation / replication / reviewer-assessment / citation-positioning / quick-summary.input_scope: full-paper / abstract-only / introduction-related-work / method-only / experiments-only / figures-tables / excerpt.paper_type: algorithmic / system / hardware / control / communications / signal-processing / survey / general.extraction_focus: contribution / method-pipeline / equations / experiments / limitations / reproducibility / related-work.output_depth: brief / standard / deep.
- State the detected axes in one short line.
- Load only the matching fragments.
- Extract a source-bounded fact base before analysis.
- Mark missing information when the input is partial.
Output Contract
Default:
Detected axes: reading_purpose=..., input_scope=..., paper_type=..., extraction_focus=..., output_depth=...
Paper kernel
- Object:
- Method:
- Condition:
- Prior limitation:
- Main contribution:
- Evidence:
Structured notes
[purpose-specific output]
Limitations / missing information
- ...
For implementation or replication, include a checklist of missing details.
For citation positioning, include how the paper should and should not be cited.
Red Lines
Do not invent paper content, equations, results, datasets, or limitations not present in the supplied material.
Do not overquote source text. Summarize and paraphrase.
If the input is only an abstract or excerpt, keep the assessment bounded.
What ships with it
36 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 233 B
- manifest.yaml 3.6 KB
- static/core/output-format.md 348 B
- static/core/stance.md 265 B
- static/core/workflow.md 371 B
- static/fragments/extraction_focus/contribution.md 168 B
- static/fragments/extraction_focus/equations.md 186 B
- static/fragments/extraction_focus/experiments.md 151 B
- static/fragments/extraction_focus/limitations.md 162 B
- static/fragments/extraction_focus/method-pipeline.md 164 B
- static/fragments/extraction_focus/related-work.md 129 B
- static/fragments/extraction_focus/reproducibility.md 185 B
- static/fragments/input_scope/abstract-only.md 169 B
- static/fragments/input_scope/excerpt.md 123 B
- static/fragments/input_scope/experiments-only.md 163 B
- static/fragments/input_scope/figures-tables.md 142 B
- static/fragments/input_scope/full-paper.md 128 B
- static/fragments/input_scope/introduction-related-work.md 191 B
- static/fragments/input_scope/method-only.md 182 B
- static/fragments/output_depth/brief.md 112 B
- static/fragments/output_depth/deep.md 162 B
- static/fragments/output_depth/standard.md 100 B
- static/fragments/paper_type/algorithmic.md 137 B
- static/fragments/paper_type/communications.md 140 B
- static/fragments/paper_type/control.md 168 B
- static/fragments/paper_type/general.md 131 B
- static/fragments/paper_type/hardware.md 141 B
- static/fragments/paper_type/signal-processing.md 160 B
- static/fragments/paper_type/survey.md 141 B
- static/fragments/paper_type/system.md 136 B
- static/fragments/reading_purpose/citation-positioning.md 265 B
- static/fragments/reading_purpose/implementation.md 234 B
- static/fragments/reading_purpose/literature-review.md 230 B
- static/fragments/reading_purpose/quick-summary.md 115 B
- static/fragments/reading_purpose/replication.md 231 B
- static/fragments/reading_purpose/reviewer-assessment.md 190 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 · 60 lines · 80 tokens per session scan A cac3b3a5dc7a
ieee-paper-reader is a skill published in the GitHub repository CloudWave818/ieee-skills (429 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 476 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-paper-reader compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ieee-paper-readerCloudWave818/ieee-skills | Skill | 429 | 2mo ago | MIT | A | 80 | Codex |
| hr-onboardingnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | yesterday | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | 24d ago | Apache-2.0 | A | 25 | Claude Code, Codex |