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.
/plugin marketplace add mgallet92i/waterfall/plugin install waterfallWrote 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.
[](https://agentmods.dev/agents/mgallet92i/waterfall/wf-or)<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>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.
| Model | Per session | Once 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 |
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.
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.mdCe 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 --queryrequires 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.
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.
- 6d ago First seen · 1,266 lines · 44 tokens per session scan A 1f07bbfddd4b
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.
Other agents, from other repositories
grainulator
Autonomous research sprint subagent. Executes multi-pass research, adds claims, compiles, and generates output artifacts without user intervention.
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 …
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…
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…
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…
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…