wf-pm

wf-pm is a skill for Claude Code from mgallet92i/waterfall. It costs 44 tokens per session (5,926 once invoked), scanned A, original, MIT.

A project-management role for the waterfall workflow, a staged development process with defined handoffs and checkpoints. It leads the team, delegates technical work, asks the human for decisions, and commits the completed result.

In plain words
What is it for?
Use it to run a full waterfall session, create and coordinate the team, collect human approvals, relay decisions, and make the final Git commit.
Why use it?
It keeps project coordination separate from implementation and review work. A single lead manages teammates, relays decisions, and controls when the workflow is closed.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the waterfall plugin — 6 skills, 3 commands, 8 agents, 1 hook shipped together

Good fit Use it to run a full waterfall session, create and coordinate the team, collect human approvals, relay decisions, and make the final Git commit.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add mgallet92i/waterfall
Claude Code
/plugin install waterfall

Made for: Claude Code.

Or install waterfall, the plugin that ships this one along with the rest of its 6 skills, 3 commands, 8 agents, 1 hook.

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 wf-pm

README.md
[![agentmods](https://agentmods.dev/badge/skills/mgallet92i/waterfall/wf-pm/github.svg)](https://agentmods.dev/skills/mgallet92i/waterfall/wf-pm)
Your own site
<a href="https://agentmods.dev/skills/mgallet92i/waterfall/wf-pm"><img src="https://agentmods.dev/badge/skills/mgallet92i/waterfall/wf-pm/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 wf-pm

Your own site · 80×15
<a href="https://agentmods.dev/skills/mgallet92i/waterfall/wf-pm"><img src="https://agentmods.dev/badge/skills/mgallet92i/waterfall/wf-pm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,926 The whole file, excluding the scripts and references it only reads on demand.
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.
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 $0.00044 $0.05926
Opus 5 $0.00022 $0.02963
Sonnet 5 $0.00009 $0.01185
Haiku 4.5 $0.00004 $0.00593

Measured 9d ago against content hash 8deaead6b62d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wf-pm 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 9d 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.

skills/wf-pm/SKILL.md · 558 lines

How it starts

The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM — Project Manager (team lead)

⚠ CONSTITUTION — Règles universelles Waterfall

Lire obligatoirement avant toute action : agents/_shared/constitution.md

Ce fichier définit : invariants universels, format SendMessage, protocole ACK, prohibitions universelles, mapping artefacts → owners, Session INV, Bash write prohibition.

Core principle

PM is the main conversation. It is the only one allowed to:

  • Agent — spawn teammates (the implicit team forms at the first spawn; no TeamCreate)
  • AskUserQuestion — interact with the HO
  • git commit — commit the final result at CLOSURE

PM is a team lead and a relay, not a technical executor. It does not write artifacts, does not code, does not review code — that's the role of specialized teammates.

INV-PM-ASK (reinforced) — Strict HO channel

Full definition : agents/wf-pm.md §INV-PM-ASK.

Any question, request, solicitation or test addressed to the HO goes exclusively through AskUserQuestion, no exception. A plain-text question (markdown, sentence ending with ?, numbered list) is a violation.

Structured options are mandatory for non-binary cases. If PM hesitates: AskUserQuestion. If nothing to ask: silence. No third option.


Brief Discipline (INV-BRIEF-DISCIPLINE)

Invariant complet : agents/_shared/constitution.md §Invariants universels — INV-BRIEF-DISCIPLINE.

Règle : toute évolution de spec ou de tâche se matérialise uniquement par l'édition de l'artefact source-of-truth désigné (specs.md, design.md, tasks.md). La mailbox ne transporte jamais de contenu de spec ni de raffinement de tâche (pas de T-xxx v2/v3 en mailbox).

Procédure après édition d'artefact :

  1. Éditer l'artefact cible (specs.md, design.md, tasks.md — section §X concernée).
  2. Envoyer un poke minimaliste aux agents concernés :
    type: poke
    note: "relire §X de <artefact> — mis à jour."
    
  3. L'agent destinataire relit l'artefact sur disque depuis §X — jamais depuis le contenu du message reçu.

Read the full file on GitHub · 558 lines

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. 9d ago First seen · 558 lines · 44 tokens per session scan A 8deaead6b62d

Subscribe to this mod's changes

wf-pm is a skill published in the GitHub repository mgallet92i/waterfall (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 5,926 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.

Related

Other skills, from other repositories

analyze

Use this skill after Phase 1 Plan to create or intake requirements for a task. Produces requirements with stable IDs (REQ-001, REQ-002, ...), validates each requirement against the project's scope statement, and — critically — halts and asks for UX designs and brand guidelines whenever the work touches a frontend or…

lantisprime/claude-sdlc · 111 tokens

gate-signoff

Use this skill to capture a human phase-gate sign-off through chat rather than requiring the user to manually edit the gate markdown file. Prompts the user with the artifact path, collects a work-item URL (REQ / ticket / CR) as the non-trivial acknowledgment, validates the URL shape against the ticket system…

lantisprime/claude-sdlc · 170 tokens

ship-it

Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality, owns the red-test fix loop, runs the docker harness with always-teardown, then drives ship-change inline. Escape hatch writes SHIPITBLOCKED.md. Runnable headless. Triggers: "ship it", "build…

BlackBeltTechnology/pi-agent-dashboard · 92 tokens

project-init

Scaffold an unconfigured directory into a configured pi project. Interactive, profile-driven: previews the planned writes, then writes AGENTS.md, .pi/settings.json and prompt files — optionally also a knowledge base, an openspec/ scaffold, and user-global /.pi/agent/settings.json. Use on a bare directory, or when the…

BlackBeltTechnology/pi-agent-dashboard · 81 tokens

execute-round

Use when a planned round handoff exists and needs to be implemented end-to-end via the 4-commit chain (entry-admin → BA design → dev body with inline CR + SE → state refresh + self-audit). Dispatches ba-designer / developer / cr-reviewer / se-contract sequentially.

Arch1eSUN/Arcgentic · 65 tokens

debt-ops-add

Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…

bcanfield/agentic-tech-debt · 115 tokens