By mgallet92i
Multi-agent specification-driven development (SDD) framework for Claude Code. Orchestrates a team of specialized agents (PM, OR, PO, TL, DV, RV, QA, DS) through a waterfall workflow from requirements to validated implementation.
> Ce fichier est la source canonique des règles communes à tous les agents Waterfall.
ui.md author in TECHNICAL_DESIGN phase, spawned only if has_ui:true in PRD.md — conditional lazy spawn.
Code + unit tests implementer in IMPLEMENTATION phase — receives T-xxx tasks from TL, codes, runs tests until PASS, notifies TL via brief_complete, follows the INV-007 pipeline (TODO→IN_PROGRESS→IMPLEMENTED→UNIT_TESTS_OK→CODE_REVIEW_OK→DONE).
PM additional instructions for the VALIDATION and CLOTURE phases.
specs/acceptance author starting at FUNCTIONAL_SPECS — reads PRD.md authored by PM, produces specs.md and acceptance.md.
Starts a new SDD need via the waterfall workflow — agent teams preflight, TeamCreate, OR spawn, bootstrap_need.
PM solo pour le mode subagent-light — élicitation, specs.md, checkpoint specs, spawn TL passe 1+2, checkpoint tasks, validation finale, git commit.
Sole team lead of the waterfall workflow — creates the team, dispatches OR's spawn_request, relays HO decisions via AskUserQuestion, and runs the final git commit at CLOSURE.
Cleanly stops the active wf workflow — shutdown teammates, marker cleanup, state preservation for resume.
Resumes an interrupted waterfall workflow — preflight, need lookup, Agent Teams team re-creation, OR handoff with resume brief.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Multi-agent Spec-Driven Development (SDD) framework for Claude Code. Waterfall orchestrates a team of specialized agents (OR, PM, PO, TL, RV, DV, QA, DS) through a strict waterfall workflow — from product brief to validated implementation — with explicit handoffs, persistent state, and identity enforcement.
🌐 Homepage: https://mgallet92i.github.io/waterfall/
Full documentation (best practices, agent roles, state machine, troubleshooting) will live on a dedicated documentation site. This README covers what you need to install and run the plugin.
Waterfall turns a single Claude Code session into a coordinated team of agents, each with a narrow role:
Each need (work item) lives under wf/needs/<kebab-name>/ with its own PRD, design, specs, tasks, tracking, and .wf-state.json. The state machine (scripts/wf-orchestrate.sh) is the single source of truth for what happens next; agents only advance via guarded --complete calls.
Built on Claude Code's experimental Agent Teams feature.
Marketplace listing coming soon. In the meantime, clone the repo and install it as a local marketplace.
<path-to-repo> (e.g. C:\repo\waterfall on Windows, ~/repo/waterfall on macOS/Linux)./plugin marketplace add <path-to-repo>
/plugin install waterfall@waterfall-local
/plugin
You should see waterfall listed and the /waterfall:new, /waterfall:resume, /waterfall:quit commands available.
The plugin ships:
commands/ — slash commands (/waterfall:new, /waterfall:resume, /waterfall:quit)agents/ — the eight agent definitions (wf-pm, wf-or, …)skills/ — skill bundles invoked by the commandshooks/wf-auth.sh — PreToolUse(Bash) identity guardscripts/ — orchestrator, watchdog, statusline, registry, preflight checkswf/templates/ — need document templates, fr and en mirrors (PRD, design, specs, tasks, …)scripts/wf-check-bash.sh enforces this on every /waterfall:new and /waterfall:resume and fails fast with a clear message otherwise..wf-state.json / ack-registry.json. The bootstrap script scripts/wf-check-jq.sh will detect and offer to install it:
winget install jqlang.jq (fallback: choco, scoop)brew install jq (fallback: port)apt-get / dnf / yum / pacman / zypper / apk (auto-detected)Semgrep — static code analysis used by TL during code review. Disabled by default; enable by setting tools.semgrep: "on" in .wf-config.json. The helper scripts/lib/wf-semgrep.sh auto-detects the available runner:
semgrep on $PATH — install via pipx install semgrep or uv tool install semgrep)semgrep/semgrep image, requires Docker Desktop running)If neither is available, TL skips Semgrep silently and the review proceeds unchanged. Findings are mapped to the existing blocker/nit scale (ERROR→P0, WARNING→P1, INFO→P2).
The default ruleset is strict: p/owasp-top-ten + p/cwe-top-25 + p/default. Override via tools.semgrep_rules (array of Semgrep registry packs or local YAML paths). Dead code and duplication detection are out of scope for Semgrep — handled by SonarCloud integration (planned, RV-side).
Agent Teams is an experimental Claude Code feature. Enable it in ~/.claude/settings.json:
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
npx claudepluginhub mgallet92i/waterfall --plugin waterfallComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.