A Claude Code plugin for a ten-phase software development workflow. It coordinates helper agents and records progress so work can resume after an interruption.

Use it for new enhancements that need codebase exploration, architecture, backend or frontend work, security review, testing and a pull request.

It provides a defined path from feature discovery to implementation and review instead of requiring each phase to be organised manually.

jidoka — Plugin for Claude Code by wei6bin/skills

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.

Clone the repo

git clone --depth 1 https://github.com/wei6bin/skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/wei6bin/skills/jidoka/github.svg)](https://agentmods.dev/plugins/wei6bin/skills/jidoka)

Your own site

<a href="https://agentmods.dev/plugins/wei6bin/skills/jidoka"><img src="https://agentmods.dev/badge/plugins/wei6bin/skills/jidoka/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/wei6bin/skills/jidoka"><img src="https://agentmods.dev/badge/plugins/wei6bin/skills/jidoka.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 20 skills cost 926 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

jidoka 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 4d 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.

.claude-plugin/marketplace.json#jidoka · 39 lines

What it actually says

{
  "name": "jidoka",
  "description": "Claude Code dev-workflow plugin. The `line` skill drives the 10-phase plan-then-build flow in the main session, dispatching helper subagents (code-explorer, code-architect, plan-reviewer, impl-backend, impl-frontend, impl-simplify, code-reviewer, security-reviewer, test-plan-walker) as needed. Loop position persists in a per-slice 07-progress.md ledger so the workflow is resumable.",
  "source": "./jidoka",
  "agents": [
    "./agents/code-architect.md",
    "./agents/code-explorer.md",
    "./agents/code-reviewer.md",
    "./agents/impl-backend.md",
    "./agents/impl-frontend.md",
    "./agents/impl-simplify.md",
    "./agents/plan-reviewer.md",
    "./agents/project-scaffolder.md",
    "./agents/security-reviewer.md",
    "./agents/test-plan-walker.md"
  ],
  "skills": [
    "./skills/aspnet-backend-scaffold",
    "./skills/backend-implementer",
    "./skills/check",
    "./skills/codebase-context-builder",
    "./skills/context-updater",
    "./skills/frontend-implementer",
    "./skills/frontend-styling-standard",
    "./skills/git-worktrees",
    "./skills/herdr-crew",
    "./skills/line",
    "./skills/project-setup",
    "./skills/raise-pr",
    "./skills/react-best-practices",
    "./skills/react-frontend-scaffold",
    "./skills/refine",
    "./skills/restful-api-design",
    "./skills/reuse-ladder",
    "./skills/sweep-implementer",
    "./skills/test-plan-walkthrough",
    "./skills/vertical-slicing"
  ]
}

Contents

What it installs

The manifest is a name and a version. 20 skills travel with it, and installing the plugin installs all of them — 926 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#jidoka 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.

marketplace.json 3.4 KB

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.

4d ago Changed · +1 lines 7cc84eb5635d
7d ago Changed · +2 lines 8de9b330026a
1mo ago Changed · +4 lines cae557462480
1mo ago First seen · 32 lines scan A 19d049e448a3

Subscribe to this mod's changes

jidoka is a plugin published in the GitHub repository wei6bin/skills (2 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-02.

Code review Planning

jidoka next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
jidokawei6bin/skills	Plugin	2	4d ago	MIT	A	—	Claude Code
han-communicationtestdouble/han	Plugin	350	2d ago	MIT	A	—	Claude Code
ai-infra-auto-driven-skillsBBuf/AI-Infra-Auto-Driven-SKILLS	Plugin	1.2k	5d ago	none	A	—	Claude Code
pedantic-coderoborchers/fractional-cto	Plugin	37	20d ago	MIT	A	—	Claude Code
git-prCasper-Studios/casper-marketplace	Plugin	14	yesterday	MPL-2.0	A	—	Claude Code
code-qualitydanielbodnar/skills	Plugin	2	2d ago	MIT	A	—	Claude Code
coderabbitThrownLemon/claude-code-plugins	Plugin	2	5mo ago	MIT	A	—	Claude Code