claudecodex

sddx

Spec-driven development with proof: one approved spec per goal, a RED/GREEN boundary proof per task, a review bound to the verified diff, and hash-chained receipts.

1 on GitHubby glapsfunv6.0.1MITupdated 10 days ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin sddx in glapsfun/sddx. Commands read from the repo's manifest — 8 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (7)

  • brainstorm

    Use when the user wants a new feature or behavior change in an sddx repository and no spec covers it yet. Turns the idea into a spec's Design through conversation, checked by sddx spec check.

  • debug

    Use when sddx verify fails and the cause is not obvious, or sddx board flags a task as stuck. Reproduces with the oracle, tests one hypothesis at a time, and pins the bug with a failing test.

  • execute

    Use when an sddx goal has tasks ready to implement. Starts each ready task, dispatches one worker per task in its own worktree, and ends every task at sddx verify.

  • finish

    Use when every task of an sddx goal is DONE. Checks the run report and the receipt chain, then opens a pull request from the goal's run branch for a person to merge.

  • plan

    Use when a spec's Design is ready and it has no Tasks yet, or its tasks need revising. Splits the design into tasks with executable oracles and disjoint scopes, then takes the plan through check, approval and start.

  • review

    Use when an sddx task is IN_REVIEW. Dispatches the critic on the verified diff in a clean context and records its verdict with sddx review record.

  • using-sddx

    Use at the start of work in a repository with .sddx/, or when the user asks to build or change something with sddx. Routes the work through brainstorm, plan, execute, review and finish, each ending at an sddx CLI gate.

Subagents (2)

  • critic

    Reviews one verified sddx task in a clean context against its spec, acceptance lines and code quality, and returns a pass or fail verdict with findings. Has no file-editing tools.

  • worker

    Implements one sddx task inside its own worktree, failing test first, and proves it with sddx verify. Dispatched by the sddx execute skill.

Hooks (8)

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook" session-start

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook" approval-gate

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook" bash-gate

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook" approval-gate

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook" tdd-gate

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook" record-test

  • Stop

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook" stop-gate

  • SubagentStop

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook" stop-gate

View source on GitHub

Problems found in this repo's manifests

  • .claude-plugin/marketplace.json is not valid JSON

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

agent-skills

claudecodex

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

addyosmani/agent-skills 116,782

agentic-qe-fleet

claude

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

superpowers

claude

Superpowers teaches Claude brainstorming, subagent driven development with built in code review, systematic debugging, and red/green TDD. Additionally, it teaches Claude how to author and test new skills.

anthropics/claude-plugins-official 47,076

Maintain sddx?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted