claude

spec-flow

Spec-driven development workflow: subagents for review/planning/verification, a deterministic progress engine, templates, a SessionStart hook, and a PreToolUse drift guard. Stop vibe-coding.

0 on GitHubby Timo Haldiv0.3.0MITupdated 4 months agoworkflow
/

Plugin spec-flow from marketplace spec-flow in Timohone/specflow. Commands read from the repo's manifest — 1 month 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 (1)

  • spec-driven-development

    Use when implementing a non-trivial feature, change, or bugfix in a codebase. Enforces a disciplined Spec -> Plan -> Build -> Verify workflow instead of jumping straight to code. Trigger when the user asks to "build", "implement", "add a feature", or "refactor" something that spans more than a trivi

Slash commands (5)

  • /spec-flow:build

    Implement the feature strictly following the approved plan, one step at a time (Build phase)

  • /spec-flow:plan

    Turn an approved spec into a codebase-grounded implementation plan (Plan phase)

  • /spec-flow:spec-status

    Show the status and progress of all specs in this repo

  • /spec-flow:spec

    Turn a feature idea into a reviewed, testable spec (Spec phase)

  • /spec-flow:verify

    Adversarially verify the implementation against the spec's acceptance criteria (Verify phase)

Subagents (3)

  • planner

    Use during the Plan phase of spec-driven development to turn an APPROVED spec into a concrete, codebase-grounded implementation plan. Invoke when a spec exists and a plan is needed before any code is written. Does not write implementation code.

  • spec-reviewer

    Use during the Spec phase to critique a DRAFT spec for testability, completeness, and scope clarity before any planning or coding begins. Invoke right after a spec is drafted to harden it.

  • verifier

    Use during the Verify phase to adversarially check an implementation against a spec's acceptance criteria, running tests and demanding evidence for every claim. Invoke after a build is complete to determine honestly whether the work is done.

Hooks (2)

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/scripts/session-context.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/scripts/drift-guard.sh"

View source on GitHub

Similar plugins

superpowers

claudecodex

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

15 skills · hooks

obra/superpowers 316,836

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

PRD generation and conversion skills for the Ralph autonomous agent loop

2 skills

snarktank/ralph 22,224

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

Maintain spec-flow?

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