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/theorata/report-skill/reportnpx skills add TheoRata/Report-Skill --skill reportgit clone --depth 1 https://github.com/TheoRata/Report-SkillWrote 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/theorata/report-skill/report)<a href="https://agentmods.dev/skills/theorata/report-skill/report"><img src="https://agentmods.dev/badge/skills/theorata/report-skill/report.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 | $0.00177 | $0.04521 |
| Opus 5 | $0.00088 | $0.02261 |
| Sonnet 5 | $0.00035 | $0.00904 |
| Haiku 4.5 | $0.00018 | $0.00452 |
Grade A, and why
report 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report skill
Convert agent research, documentation, code analysis, and technical write-ups into a designed HTML report instead of raw Markdown. The user reads these in the browser; the page handles light/dark theme, table of contents, footnotes, code blocks, callouts, framed figures with click-to-zoom, and one-click export back to Markdown.
When this triggers
Any time the natural output would be a .md file with headings, multiple sections, and more than ~500 words. Specifically:
- "Write me a report / deep-dive / summary / analysis on X"
- "Investigate X and document what you find"
- "Research X and give me your findings"
- "Postmortem the Y incident"
- "Document the Z system / architecture / decision"
- "Write up the conclusions from our discussion"
- "Compare X and Y in detail"
Skip this skill for: quick conversational answers, single-file code edits, status updates, one-line confirmations, anything under ~300 words. The user wants this for real reports, not for every response.
The workflow
- Write the report as Markdown with YAML frontmatter (see Frontmatter and Markdown syntax below). Save it to the project's
reports/directory. - Run the renderer:
This producesnode ~/.claude/skills/report/render.mjs reports/your-report.mdreports/<title-slug>-<date>.htmlin the same directory. - Tell the user where to open it. Provide the absolute file path; they open it in their browser.
The cost: the agent writes Markdown only. Token spend is identical to writing a plain .md file. The HTML is generated mechanically by the renderer.
Editing an existing report
When the user asks to update, edit, modify, or expand an existing report — do not re-write it from scratch. Edit the source Markdown and re-render. This preserves footnotes, tags, structure, and keeps the diff small.
Two cases:
Case A — the source .md still exists (it always does, if the report was rendered into reports/):
What ships with it
16 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.
- build-index.mjs 7.0 KB runs code
- build-index.test.mjs 9.4 KB runs code
- clean-comments.mjs 1.6 KB runs code
- comment-popup.test.mjs 17 KB runs code
- comments.mjs 8.3 KB runs code
- comments.test.mjs 26 KB runs code
- example.html 108 KB
- extract.mjs 1.9 KB runs code
- index-template.html 12 KB
- motion.test.mjs 7.4 KB runs code
- render-sweep.test.mjs 3.6 KB runs code
- render.mjs 33 KB runs code
- review-summary.mjs 813 B runs code
- review.mjs 11 KB runs code
- template-overlay.test.mjs 2.0 KB runs code
- template.html 128 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.
- 5d ago First seen · 387 lines · 0 tokens per session scan A 4cd7eb0a3570
report is a skill published in the GitHub repository TheoRata/Report-Skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 177 tokens to every session and 4,521 once invoked, about $0.0009 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
markdown-enhancer
Markdown处理(目录生成、链接检查、表格格式化、统计、Lint、转HTML).
documentation-patterns
Technical documentation patterns for READMEs, ADRs, API docs (OpenAPI 3.1), changelogs, and writing style guides. Use when creating project documentation, writing architecture decisions, documenting APIs, or maintaining changelogs.
hwp
Use this skill whenever the user wants to read, create, or edit Korean Hangul Word Processor documents (.hwp or .hwpx files). Triggers include any mention of 'hwp', 'hwpx', '한글 문서', '아래한글', '한컴오피스', or uploading/attaching .hwp/.hwpx files. Also use when extracting text from Korean reports or producing Korean-formatted…
format-converter-brief
Produces a clear, step-by-step brief explaining exactly how to convert a finished article or document from one format (Word, plain text, InDesign export) into a specified target format (Markdown, HTML, or structured plain text), preserving all editorial elements correctly.
html-to-pptx
当用户想把 HTML 幻灯片转成 .pptx 时触发——"HTML 转 PPT"、"网页幻灯片转 pptx"、"把这个 deck 转成 ppt"、"给同事一份 ppt 副本"、"汇报不方便放浏览器"、给了 .html 路径 + 提到 ppt/pptx/演示/幻灯片。保留矢量文字可编辑、字体按需嵌入、复杂装饰自动走截图兜底;不依赖 reveal.js / 自写 deck 等具体框架。.
proofpress
Preserve or inspect decision history for Markdown and static HTML knowledge artifacts with Proofpress. Use when creating or accepting a meaningful revision to an ADR, design doc, PRD, README, strategy note, portable .md artifact, or static .html/.htm artifact in a configured repository, or when receiving a file…