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/hazat/pi-config/visualize-plannpx skills add HazAT/pi-config --skill visualize-plangit clone --depth 1 https://github.com/HazAT/pi-configWrote 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/hazat/pi-config/visualize-plan)<a href="https://agentmods.dev/skills/hazat/pi-config/visualize-plan"><img src="https://agentmods.dev/badge/skills/hazat/pi-config/visualize-plan.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 | $0.00057 | $0.00930 |
| Opus 5 | $0.00028 | $0.00465 |
| Sonnet 5 | $0.00011 | $0.00186 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
visualize-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualize Plan
Transform an existing plan into a faithful, polished HTML explanation. Do not review, rewrite, execute, or expand the plan into new requirements.
Step 1: Resolve the plan
Resolve the plan source in this order:
- If the input names a readable file, use that file. Treat the full input as one path after removing optional surrounding quotes or a leading
@. - If the input is empty, derive the session file (
PI_SESSION_FILE, or in Claude Code$HOME/.claude/projects/<project slug>/$CLAUDE_CODE_SESSION_ID.jsonlwith/and.in the project path mapped to-) and use${SESSION_FILE%.jsonl}.plan.mdwhen it exists. - If the input contains substantial inline plan content, use it directly.
- Otherwise, stop and ask for a plan file path or pasted plan.
For path-like input that does not exist, report the missing path; do not reinterpret it as plan text. Read the complete plan before generating anything.
Step 2: Load the visual system
Load the visual-explainer skill and follow its full-HTML workflow, design rules, reference routing, and delivery checklist. Do not use quick mode: implementation plans need custom hierarchy and composition.
Use only the source plan unless the user explicitly asks to verify it against the repository. Do not research the codebase merely because the plan mentions files or symbols.
Step 3: Inventory the source
Create a private coverage inventory of every substantive source section, including:
- goal, intent, and selected approach;
- in-scope and out-of-scope boundaries;
- architecture, data flow, or behavior changes actually stated in the plan;
- implementation phases and dependencies;
- affected files, interfaces, contracts, and migrations;
- acceptance criteria and verification commands;
- assumptions, risks, rejected alternatives, and repository evidence.
Preserve exact commands, paths, identifiers, and acceptance-criterion IDs. Never invent missing architecture, dependencies, evidence, or requirements. Use cards or prose when the source does not justify a diagram.
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 · 87 lines · 57 tokens per session scan A 557aee467339
visualize-plan is a skill published in the GitHub repository HazAT/pi-config (443 stars, last pushed 10d ago), licensed MIT. It adds 57 tokens to every session and 930 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.