agentmods.dev

auto-concept

auto-concept is a skill for Claude Code from Jerry0022/dotclaude. It costs 139 tokens per session (8,981 once invoked), scanned C, a copy of bibi, MIT.

A tool that creates an interactive web page for plans, analyses, design ideas, prototypes, comparisons, or creative work. It opens the page in a browser and brings back the user's choices and comments.

In plain words
What is it for?
Use it to present alternatives, mockups, plans, or prototypes in an interactive page. It can also capture selections, toggles, and comments for the next step.
Why use it?
It turns a discussion into something the user can inspect and respond to instead of relying only on text. This helps collect decisions while the work is being developed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the devops plugin — 18 skills, 12 agents, 9 hooks, 1 MCP server shipped together

not rated 6repo changed 11d ago C scan 139 tokens copy · 86% MIT

Good fit Use it to present alternatives, mockups, plans, or prototypes in an interactive page. It can also capture selections, toggles, and comments for the next step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jerry0022/dotclaude/auto-concept
View source ↗ Jerry0022/dotclaude
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.

Any agent
npx skills add Jerry0022/dotclaude --skill auto-concept
Clone the repo
git clone --depth 1 https://github.com/Jerry0022/dotclaude

Made for: Claude Code.

Or install devops, the plugin that ships this one along with the rest of its 18 skills, 12 agents, 9 hooks, 1 MCP server.

Wrote 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.

agentmods badge for auto-concept

README.md
[![agentmods](https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-concept/github.svg)](https://agentmods.dev/skills/jerry0022/dotclaude/auto-concept)
Your own site
<a href="https://agentmods.dev/skills/jerry0022/dotclaude/auto-concept"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-concept/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.

agentmods 80×15 button for auto-concept

Your own site · 80×15
<a href="https://agentmods.dev/skills/jerry0022/dotclaude/auto-concept"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-concept.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,981 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 86% copy Near-identical to another mod 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 5.1 $0.00139 $0.08981
Opus 5.5 $0.00056 $0.03592
Sonnet 5.5 $0.00028 $0.01796
Haiku 4.5 $0.00014 $0.00898

Measured 11d ago against content hash 61482b0b41e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

auto-concept scanned grade C with 2 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 11d ago.

The scan reads SKILL.md. This mod also ships 14 executable files (analysis-modes.test.js, analysis-ui.test.js, anno-bubble-redesign.test.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.

**UNPROCESSED guard — never discard unseen work.** Before any `rm -rf` of a

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Read, Write, Glob, Grep, Bash(start *), Bash(cmd *), Bash(python *), Bash(curl *), Bash(kill *), Bash(node *), AskUserQuestion, CronCreate, CronDelete, mcp__Claude_Browser__*, mcp__Claude_Preview__*, mcp__
Origin

This is a copy

86% identical to bibi — 567 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/devops/skills/auto-concept/SKILL.md · 491 lines

How it starts

The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Concept

Generate an interactive HTML page for $ARGUMENTS, open it in the browser, and monitor for user decisions.

No reachable bridge ≠ no concept

A concept request always produces this skill's page: the templates.md engine, a template and content variant, the decision panel, the validation gate, the file under docs/concepts/. The bridge is mandatory wherever it can run — every Desktop or local CLI session runs Step 3 unchanged. Only a session whose owner cannot reach a localhost bridge (a claude.ai cloud or remote container, no local browser) takes the fallback in Step 3 § No reachable bridge — and even there only the transport changes, never the page. A hand-built look-alike page with its own decision storage is never a substitute (#568).

Step 0 — Load Extensions

Injected by the override loader ([skill-overrides] block); none shown → none exist.

Step 0.5 — Concept Mode (asked once, at the start)

Before Step 1 runs for the first iteration, settle which kind of concept the user wants. Three modes exist:

Mode What the page is Templates in scope
decision Pure decision concept — non-visual alternatives to weigh (architecture, strategy, library, approach, …) decision (plus free for surrounding analysis) — no mockups
design Pure design concept — visual directions / mockups / click-dummies design only — no decision views, no decision iteration
mixed Both — the visual call AND the non-visual calls belong to the same concept design iteration(s) carrying decision views where the question is about the mock, and/or a separate decision iteration where it stands on its own (entangled-questions rule in 1a)

Before executing this step, Read deep-knowledge/step1-templates.md § Step 0.5 · Asking, the do-batch start, count preferences completely — ask exactly ONE AskUserQuestion (mixed first, "(Recommended)") unless the prompt names or unambiguously implies the mode or a caller pins the template — then skip it; lean to mixed when the prompt allows two readings; no "Erstmal in Ruhe durchlesen" prefix; a typed "Other" is a real answer; a --from=do-batch start derives the mode from its open decisions and never drops a coverage line; the mode is decided once per concept and feedback widens it silently; plus the count preferences (7 alternatives, 3 designs, top 3–7 annotations — the user's count wins).

Read the full file on GitHub · 491 lines

Files

What ships with it

60 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.

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. 11d ago Changed · +50 lines 61482b0b41e4
  2. 12d ago Changed 1e0a9c5def2d
  3. 14d ago Changed · +4 lines c5cdf6c5ceb9
  4. 16d ago Changed · -3 lines 2e8bb9cf879f
  5. 18d ago Changed · +9 lines 2eda69792bd7
  6. 21d ago Changed · -68 lines 798fb7de01e0
  7. 23d ago Changed · +11 lines df06f1ebebed
  8. 1mo ago Changed · -1,750 lines 8f287d9244d7
  9. 1mo ago Changed f312d472a136
  10. 1mo ago First seen · 2,238 lines · 139 tokens per session scan C 08f3f8fa8c05

Subscribe to this mod's changes

auto-concept is a skill published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 139 tokens to every session and 8,981 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). It is 86% identical to bibi, differing in 567 lines, and is treated as a copy.

Design and UXPlanning
Related

auto-concept compared with skills from other repositories

auto-concept next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
auto-conceptJerry0022/dotclaudeSkill611d agoMITC139Claude Code
webgl-holographic-foilnexu-io/open-designSkill106kyesterdayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill106kyesterdayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill106kyesterdayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34k3d agoMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6kyesterdayMITA47Claude Code