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 Pawel-Kica/claude-code-100 --skill html-planninggit clone --depth 1 https://github.com/Pawel-Kica/claude-code-100Wrote 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/pawel-kica/claude-code-100/html-planning)<a href="https://agentmods.dev/skills/pawel-kica/claude-code-100/html-planning"><img src="https://agentmods.dev/badge/skills/pawel-kica/claude-code-100/html-planning/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/pawel-kica/claude-code-100/html-planning"><img src="https://agentmods.dev/badge/skills/pawel-kica/claude-code-100/html-planning.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00031 | $0.00738 |
| Opus 5 | $0.00015 | $0.00369 |
| Sonnet 5 | $0.00006 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
html-planning 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 8d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run /grilling and follow all of it. Already grilling → just keep going. This only changes where the questions land.
The one override
The whole frontier ships as one HTML page instead of one question at a time in the terminal. The page is the workspace and the input surface, the terminal carries one line per round.
Don't invent questions to fill a page. The frontier decides how many there are.
The file
~/.claude/html-planning/<topic-slug>.html, one file per topic, same path for the whole plan.
File already exists → read it first. Its DECIDED and HISTORY consts are the source of truth: rebuild the tree from them and resume. Never re-ask what HISTORY already answers.
A round
- Copy
template.htmlto the file. FillTOPIC,DECIDED,HISTORY,Q. Leave the machinery below them untouched. - Round 1 only:
open -a "Google Chrome" "file://<path>". The plan page is the only thing you ever open. Nothing else gets a tab. - Later rounds: rewrite the file, print one line ("round 3, 6 questions, refresh"). The tab is already open.
- The user hits Copy Answers and pastes the markdown back. Move that round into
HISTORY, promote what is settled intoDECIDED, recompute the frontier, regenerate.
Writing the questions
- Exactly one
rec: trueper question. That is grilling's➡️on the page. - Wireframe cards (
cards: true) when the options differ in shape and words cannot carry it. Otherwise plain text options. - Every question takes free text on top of its options, so options are a starting point, not a cage.
- Sections group a long round.
Artifacts
Some questions need a look, a feel, a motion, a layout. Build the thing and put it inside the plan page, as part of the question.
- Never open an artifact in its own tab, window or preview. The user asked for a plan, not a demo. A stray tab is an interruption.
- Keep it beside the plan as
~/.claude/html-planning/<topic-slug>-<what>.htmland embed it:n:renders raw HTML, so<iframe src="<topic-slug>-<what>.html" style="width:100%;height:760px;border:1px solid var(--line);border-radius:10px">drops a live, playable artifact straight into the question. - Interactive goes in as an iframe. A static comparison can go in as
<img>. /throwaway-prototypebuilds one fast, with two overrides. Save it beside the plan as above, and skip its "open in Chrome once" step. It gets embedded, not opened.- One artifact per question. Variants belong to a switcher inside the artifact, not to four separate files.
What ships with it
1 file 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.
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.
- 8d ago First seen · 48 lines · 31 tokens per session scan A d668bf6de25e
html-planning is a skill published in the GitHub repository Pawel-Kica/claude-code-100 (2 stars, last pushed 15d ago), licensed MIT. It adds 31 tokens to every session and 738 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…