html-report

A guide for creating a self-contained HTML report that explains a complex topic in a browser. It uses structured tables, evidence cards, diagrams or graphs when useful, and accessible tabs for long content.

In plain words
What is it for?
Use it for diagnostic reports, investigations, architecture explanations, implementation guides, technical decisions, research summaries, or operational plans when the subject is complex enough to need a document.
Why use it?
It turns multi-step technical findings or decisions into a readable document that works locally and when printed, without needing a build process.

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/firstp1ck/pi-coding-agent-forge/html-report
Any agent
npx skills add Firstp1ck/pi-coding-agent-forge --skill html-report
Clone the repo
git clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forge

Made for: Claude Code, Codex.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,444 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00067 $0.02444
Opus 5 $0.00034 $0.01222
Sonnet 5 $0.00013 $0.00489
Haiku 4.5 $0.00007 $0.00244

Measured 2d ago against content hash 81c76d99b8de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

html-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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/validate_report.py, tests/test_skill_contract.py), 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.

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.

pi-skill-html-report/skills/html-report/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HTML Report

Create source-grounded, browser-readable explanation reports with the approved dark navy visual system. The output is a document, not an application: it should open locally without a build step, remain understandable when printed, and use visuals only when they clarify real information.

When to Use

Use this skill when both are true:

  • The user requests an HTML page/report or clearly wants a browser-readable artifact.
  • The subject is complex or multi-step: diagnostics, investigations, implementation guidance, architecture, technical decisions, comparisons, research synthesis, or operational plans.

Do not use it for:

  • Short answers that do not warrant a file.
  • Slide presentations; use a presentation-specific skill instead.
  • Product dashboards, landing pages, or application UI implementation.
  • A generic technology comparison unless the user requests an HTML report.
  • Content whose evidence is too incomplete to explain responsibly; collect evidence or mark uncertainty first.

Should trigger

  • “Create a self-contained HTML report explaining this multi-stage incident with evidence, diagrams, and recommendations.”
  • “Turn this architecture analysis into a polished browser-readable explanation.”
  • “Make an HTML implementation guide with a process diagram, overview, risks, and phased steps.”
  • “Research these options and deliver a detailed HTML decision document.”

Should not trigger

  • “Explain this error in three bullets.”
  • “Build an interactive product analytics dashboard.”
  • “Create a 16:9 HTML slide deck.”
  • “Compare React and Vue and recommend one.”

Invocation Design

  • Invocation mode: model-invoked after the package is explicitly enabled.
  • Leading concept: HTML explanation report.
  • Trigger branches:
    1. Complex or multi-step explanation explicitly requested as HTML.
    2. Technical diagnostic, guide, analysis, investigation, or synthesis needing a standalone browser report.
  • The package is a disabled draft until the user explicitly installs/enables it; creation alone must not modify Pi settings.

Read the full file on GitHub · 202 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 · 202 lines · 67 tokens per session scan A 81c76d99b8de

Subscribe to this mod's changes

html-report is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (74 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 2,444 once invoked, about $0.0003 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.