agentmods.dev

wf-pm

wf-pm is an agent for Claude Code from mgallet92i/waterfall. It costs 17 tokens per session (9,910 once invoked), scanned A, original, MIT.

A set of instructions for a project-manager role in a Waterfall development workflow, where work passes through defined planning, validation, and closing stages.

In plain words
What is it for?
Use it to coordinate the workflow's validation and closing phases, assign supporting roles, read required project records, and deliver the expected outputs.
Why use it?
It clarifies who owns each stage, which documents to read, and what each phase must produce, while preventing the role from being started incorrectly.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

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

not rated 2 1mo ago A scan 17 tokens original MIT
View the source file mgallet92i/waterfall mgallet92i.github.io
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.

agentmods
npx agentmods add agents/mgallet92i/waterfall/wf-pm
Clone the repo
git clone --depth 1 https://github.com/mgallet92i/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/agents/mgallet92i/waterfall/wf-pm.svg)](https://agentmods.dev/agents/mgallet92i/waterfall/wf-pm)
Your own site
<a href="https://agentmods.dev/agents/mgallet92i/waterfall/wf-pm"><img src="https://agentmods.dev/badge/agents/mgallet92i/waterfall/wf-pm.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,910 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.09910
Opus 5 $0.00009 $0.04955
Sonnet 5 $0.00003 $0.01982
Haiku 4.5 $0.00002 $0.00991

Measured 5d ago against content hash 34e76b659999, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

agents/wf-pm.md · 854 lines

How it starts

The opening of the file, as written. The whole thing — 854 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM — Additional instructions

⚠️ Never spawn PM as a subagent via Agent(subagent_type: waterfall:wf-pm). The PM role is held by the HO (main Claude) via Skill({name: "wf-pm"}). It owns TeamCreate and Agent to create the team and spawn the other teammates (OR, PO, TL, RV, DV, QA, DS). If you are instantiated as a subagent (context wrapped in <brief> coming from main), this is an error: immediately send a SendMessage to team-lead explaining the error and approve any shutdown_request received. Do not create a team, do not spawn anything.

⚠ CONSTITUTION — Règles universelles Waterfall

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

Ce fichier définit : invariants universels, format SendMessage, livraison native des messages, prohibitions universelles, mapping artefacts → owners, Session INV, Bash write prohibition.

Phase responsibilities

À réception d'un trigger, localiser la ligne correspondant à phase + step, lire les artéfacts Inputs to Read (chemin = need_dir + colonne), produire Output to Write, exécuter Self-complete.

Phase Step Inputs to Read Output to Write Self-complete
REQUIREMENTS COLLECT_PRD (interview HO via AskUserQuestion) PRD.md --complete REQUIREMENTS:COLLECT_PRD
REQUIREMENTS GENERATE_PRD PRD.md PRD.md (no-op si déjà écrit) --complete REQUIREMENTS:GENERATE_PRD
CLOSURE BILAN or.log, tracking.md, .wf-state.json retro.md --complete CLOSURE:BILAN
CLOSURE PR_CREATE retro.md (PR GitHub) --complete CLOSURE:PR_CREATE --params pr_url=<url>

INV-PM-NOPING — PM scope restreint aux steps légitimes

Many --complete steps belong to OR, TL or other agents. PM must not attempt --complete on these — the auth hook blocks them.

Do not memorize or re-encode the step→agent mapping here (single source of truth: scripts/wf-step-agents.sh + resolve_step_agent, exposed at runtime). PM's source of truth is the agent field of wf-orchestrate.sh --query, re-read at the moment of acting:

  • agent == "pm" → PM executes the step (follow the hint field) and --complete it.
  • agent != "pm" → PM never touches --complete for that step. If PM receives a PLEASE_COMPLETE_STEP for it anyway, PM forwards it back to OR via SendMessage type=MISROUTED_TO_PM.

Read the full file on GitHub · 854 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. 5d ago First seen · 854 lines · 17 tokens per session scan A 34e76b659999

Subscribe to this mod's changes

wf-pm is an agent published in the GitHub repository mgallet92i/waterfall (2 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 9,910 once invoked, about $0.0001 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.

Project managementagent-frameworkagenticclaudeclaude-aiclaude-codeclaude-code-plugin
Related

Other agents, from other repositories

grainulator

Autonomous research sprint subagent. Executes multi-pass research, adds claims, compiles, and generates output artifacts without user intervention.

grainulation/grainulator · 29 tokens

scope-ingest

Bounded subagent that turns raw source material (markdown files, plain-text files, pasted text) into a normalized, provenance-traced scope draft at .claude/sdlc/scope-drafts/. Invoked by the plan skill when scope.md does not yet exist and the human points at a source. Write scope is restricted to scope-drafts/ only …

lantisprime/claude-sdlc · 85 tokens

maintainer-code-quality-reviewer

Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Reviews the current diff for code-quality concerns: correctness against requirements, readability and naming, anti-overengineering (matching minimal-code skill heuristics), dead code, error-path coverage. Spawned in parallel with the other…

lantisprime/claude-sdlc · 0 tokens

maintainer-dependency-reviewer

Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Conditionally reviews dependency manifest changes (package.json, requirements.txt, go.mod, Gemfile, pom.xml, Cargo.toml, lockfiles) for new-dep justification, version pinning, license, and maintainer activity. Self-exits with a…

lantisprime/claude-sdlc · 121 tokens

maintainer-security-reviewer

Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Reviews the current diff for security concerns from the security-review skill checklist (input validation, authN/authZ, secrets, injection surfaces, dependency hygiene, sensitive data, output encoding, error handling, cryptography, infra…

lantisprime/claude-sdlc · 105 tokens

maintainer-test-adequacy-reviewer

Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Reviews the current diff and the touched test files for test-adequacy concerns: coverage of changed lines, missing edge-case and failure-path tests, integration vs unit balance, no test-only mocks that mask production behavior. Spawned in…

lantisprime/claude-sdlc · 0 tokens