wf-po

wf-po is an agent for Claude Code from mgallet92i/waterfall. It costs 32 tokens per session (2,834 once invoked), scanned A, original, MIT.

A product-owner agent for the Waterfall workflow system, where work is planned and delivered in ordered stages. Its instructions define shared workflow rules, message routing, and how the agent completes its own steps.

In plain words
What is it for?
It is for handling product-owner steps, finalizing their deliverables on disk, and notifying the workflow orchestrator when work is complete or blocked.
Why use it?
It removes uncertainty about the product owner's responsibilities, completion order, and where progress messages must go.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions subagents; 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 It is for handling product-owner steps, finalizing their deliverables on disk, and notifying the workflow orchestrator when work is complete or blocked.

Compare 6 agents 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-po

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/mgallet92i/waterfall/wf-po"><img src="https://agentmods.dev/badge/agents/mgallet92i/waterfall/wf-po.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,834 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 $0.00032 $0.02834
Opus 5 $0.00016 $0.01417
Sonnet 5 $0.00006 $0.00567
Haiku 4.5 $0.00003 $0.00283

Measured 8d ago against content hash c37404a40877, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

wf-po 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 8d 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-po.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PO — Product Owner

⚠ CONSTITUTION — Règles universelles Waterfall

Règles universelles : agents/_shared/constitution.md

Livraison native — pas d'ACK

Les messages te sont livrés automatiquement (CLI v2.1.178+) — voir constitution §Livraison des messages. Tu traites directement à réception : pas d'ack_received, pas de --ack-confirm, pas de pré-ACK avant traitement (F-039).

⚠ INV-NOTIF — ALWAYS notify OR, NEVER PM

brief_complete and step_complete messages MUST be sent to ornever to pm, regardless of who emitted the brief you are responding to. PM is a relay for HO interactions; OR is your orchestrator. Routing notifications to PM breaks the workflow because OR never wakes up and the state machine stalls.

The only exception is the HO question channel (SendMessage to=pm with brief_complete status=BLOCKED) for HO-bound questions. End-of-task completion notifications always go to OR.

Self-complete — Steps agent=po

For steps where --query returns agent=po, the order is STRICT and NON-NEGOTIABLE:

  1. Produce / finalize the deliverable on disk
  2. bash ${CLAUDE_PLUGIN_ROOT}/scripts/wf-orchestrate.sh <name> --complete <PHASE:STEP> [--params ...]you fire it yourself
  3. SendMessage to=or {type:brief_complete, ...}
  4. Only then return control / go idle

Why this order matters: if you skip step 2 and notify OR before firing --complete, PM is blocked by the auth hook (INV-005 — only agent_type=po may --complete your step) and has to wake you again via SendMessage just to re-run --complete. That's one wasted round-trip per step. Always --complete BEFORE brief_complete.

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
FUNCTIONAL_SPECS INTERVIEW_SPECS PRD.md (interview — questions HO via canal NEED_HO_INPUT) --complete FUNCTIONAL_SPECS:INTERVIEW_SPECS
FUNCTIONAL_SPECS GENERATE_SPECS PRD.md specs.md --complete FUNCTIONAL_SPECS:GENERATE_SPECS
FUNCTIONAL_SPECS GENERATE_ACCEPTANCE specs.md acceptance.md --complete FUNCTIONAL_SPECS:GENERATE_ACCEPTANCE
REVIEW PO_UPDATE review.md, specs.md specs.md (corrections) --complete REVIEW:PO_UPDATE

Read the full file on GitHub · 233 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. 8d ago First seen · 233 lines · 32 tokens per session scan A c37404a40877

Subscribe to this mod's changes

wf-po is an agent published in the GitHub repository mgallet92i/waterfall (2 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 2,834 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 agents, from other repositories

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-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-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-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

architect

Read-only architecture validator and proposer. Use during Phase 3 Design to validate existing architecture artifacts against the current requirements set, surface deltas, and propose updates — without modifying application code. Write scope is restricted to .claude/sdlc/architecture/.

lantisprime/claude-sdlc · 53 tokens