codemie-html-report

Ein Leitfaden zum Erstellen statischer HTML-Seiten, Berichte, Dashboards und Statusseiten im Design von CodeMie beziehungsweise EPAM AI/Run. Er legt dafür eine dunkle Benutzeroberfläche, einheitliche Abstände, Farben und Komponenten fest.

In plain words
What is it for?
Für eigenständige HTML-Berichte, Analyse- und Übersichtsseiten, Statusseiten sowie Datenvisualisierungen. Er kann auch als Teil einer Analysepipeline verwendet werden.
Why use it?
Er sorgt dafür, dass neue HTML-Seiten wie zusammengehörige Teile derselben Anwendung aussehen. Das erspart die wiederholte Festlegung des visuellen Grundstils.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/codemie-ai/codemie-code/codemie-html-report
Any agent
npx skills add codemie-ai/codemie-code --skill codemie-html-report
Clone the repo
git clone --depth 1 https://github.com/codemie-ai/codemie-code

Made for: Claude Code, Codex.

Per session 193 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,475 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00193 $0.03475
Opus 5 $0.00097 $0.01737
Sonnet 5 $0.00039 $0.00695
Haiku 4.5 $0.00019 $0.00347

Measured 2d ago against content hash 6a2defde3f51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

codemie-html-report scanned grade C with 1 finding 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/inject-css.js, scripts/inject-data.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "<OUT>"
src/agents/plugins/claude/plugin/skills/codemie-html-report/SKILL.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeMie HTML Report Builder

You are building a standalone HTML page that visually matches the CodeMie (EPAM AI/Run) product UI. The design system is a dark-first, professional theme with Inter font, subtle borders, and semantic color tokens. Every page you produce should feel like a native screen of the CodeMie platform.

Step 1 — CSS placeholder

Do NOT read any CSS files. Do NOT inline any CSS yourself.

In the <style> block write exactly this one token as the only content:

/* __CODEMIE_CSS__ */

A post-processing script will replace this token with the full design system CSS after you write the file. All component classes are documented in Steps 3 and 4 — use them freely without reading the source files.

Step 1.5 — Data placeholders (analytics pipeline only — skip for standalone use)

Backwards compatibility: This step applies only when this skill is invoked from the codemie-analytics skill as part of its report pipeline. If you are generating a standalone HTML page directly for a user request, skip this step entirely and embed any data inline as regular JS variables.

When invoked from codemie-analytics, all JS data arrays must use /*__DATA:name__*/ placeholders instead of inline values. The analytics skill's inject-data.js step replaces these after the HTML file is written.

<script>
  /* Data is injected by inject-data.js after this file is written — do NOT hardcode arrays */
  const LEADERBOARD = /*__DATA:leaderboard-top__*/;
  const SUMMARIES   = /*__DATA:summaries__*/;
  const LLM_DATA    = /*__DATA:llms-usage__*/;
</script>

Rules for analytics-pipeline placeholders:

  • The placeholder name must exactly match the JSON filename without the .json extension. /*__DATA:leaderboard-top__*/ is only replaced when leaderboard-top.json exists. Wrong name → the placeholder is silently skipped by inject-data.js.
  • Every JS variable populated from an API response must use a placeholder.
  • Hardcoded lookup tables (tier colours, dimension labels, etc.) are fine as regular JS.
  • Never mix placeholders with inline data in the same variable declaration.

Read the full file on GitHub · 365 lines

Changes

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.

  1. 2d ago First seen · 365 lines · 193 tokens per session scan C 6a2defde3f51

Subscribe to this mod's changes

codemie-html-report is a skill published in the GitHub repository codemie-ai/codemie-code (276 stars, last pushed 3d ago), licensed Apache-2.0. It adds 193 tokens to every session and 3,475 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens