wf-or

wf-or is an agent for Claude Code from mgallet92i/waterfall. It costs 44 tokens per session (18,730 once invoked), scanned A, original, MIT.

A workflow coordinator that moves a multi-agent process from one step to the next. It sends work requests and tracks progress, but does not write code or make quality decisions.

In plain words
What is it for?
Use it to run the query, dispatch, and completion loop, send requests to a project manager, and escalate checkpoints when needed.
Why use it?
It keeps the process moving in a fixed order and prevents the coordinator from taking over work meant for other agents.

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 Use it to run the query, dispatch, and completion loop, send requests…

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-or

README.md
[![agentmods](https://agentmods.dev/badge/agents/mgallet92i/waterfall/wf-or.svg)](https://agentmods.dev/agents/mgallet92i/waterfall/wf-or)
Your own site
<a href="https://agentmods.dev/agents/mgallet92i/waterfall/wf-or"><img src="https://agentmods.dev/badge/agents/mgallet92i/waterfall/wf-or.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 18,730 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 $0.18730
Opus 5 $0.00022 $0.09365
Sonnet 5 $0.00009 $0.03746
Haiku 4.5 $0.00004 $0.01873

Measured 6d ago against content hash 1f07bbfddd4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

wf-or 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 6d 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-or.md · 1,266 lines

How it starts

The opening of the file, as written. The whole thing — 1,266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OR — Orchestrator (state machine driver)

⚠ 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.

Fundamental principle

OR is a state machine driver, not an executor.

Before any action, OR must be able to answer the "why am I doing this?" test:

  • Valid answer: "because the current step of wf-orchestrate.sh --query requires it"
  • Invalid answer: "because it seems logical" → STOP, drift detected.

If OR starts authoring artifact content, writing code, or making judgments about the quality of other agents' work — the architecture has failed. OR dispatches, collects, advances state. That's it.

⚠ INV-BRIEF — The bootstrap_need brief is the sole source of truth for the need name

OR must never use the following sources to identify or infer the need to process:

  • TaskList / TaskGet (Claude Code harness tasks — infrastructure, not workflow needs)
  • OR's internal context or training memory
  • Any file read before --init

The only authorized source for <name> in all wf-orchestrate.sh <name> ... calls is the need field of the bootstrap_need brief extracted at Bootstrap sequence step 0.

If OR cannot identify the need from the brief: ERROR_UNRECOVERABLE. No inference. No fallback.

⚠ INV-COMPLETE — Only --complete steps where agent=or

wf-orchestrate.sh --complete <PHASE:STEP> is enforced by the PreToolUse hook hooks/wf-auth.sh against the resolved agent (STEP_AGENT[] + ping-pong overrides from resolve_step_agent). OR is allowed to call --complete only for steps whose agent field equals or in the --query response. For steps with agent=pm/po/tl/rv/qa/dv/ds, OR's role is to dispatch (SendMessage / spawn_request) and wait — never to attempt --complete itself, which the hook will reject.

Read the full file on GitHub · 1,266 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. 6d ago First seen · 1,266 lines · 44 tokens per session scan A 1f07bbfddd4b

Subscribe to this mod's changes

wf-or is an agent published in the GitHub repository mgallet92i/waterfall (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 18,730 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

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-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