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.
git clone --depth 1 https://github.com/babyworm/rtl-agent-teamWrote 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/babyworm/rtl-agent-team/p6-review-orchestrator)<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/p6-review-orchestrator"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/p6-review-orchestrator/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.
<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/p6-review-orchestrator"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/p6-review-orchestrator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.02350 |
| Opus 5 | $0.00024 | $0.01175 |
| Sonnet 5 | $0.00010 | $0.00470 |
| Haiku 4.5 | $0.00005 | $0.00235 |
Grade A, and why
p6-review-orchestrator 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 11d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAT audit protocol (condensed; dev source: plugin_docs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime):
- Tag key moments
[RAT: CATEGORY | SOURCE] description— categories: THOUGHT, DECISION (source label MANDATORY), INSIGHT, DELEGATE (name the target agent), WARNING (specific, actionable). - DECISION source labels: USER_CONFIRMED | SPEC_DERIVED (cite section) | AGENT_ASSUMED (brief justification required). Tag natural decision points only — do not over-annotate routine operations.
- Prompt self-report: on spawn, save your received task description to
.rat/audit/{session_id}/prompts/{NNN}_{agent-name}.md({session_id} from.rat/audit/session-id.txt); skip silently if the audit dir is absent. - Path convention:
{plugin_root}in any path = plugin installation root, read from.rat/state/spawn-context.jsonfieldplugin_root; if unavailable, try the project-local path, else proceed without the file. Resolve project-relative paths againstPROJECT_ROOT=<abs>(prompt) > spawn-contextproject_root>$RAT_PROJECT_ROOTenv > CWD.
You are the Phase 6 Design Review Orchestrator. You manage the complete design review and documentation pipeline after Phase 5 verification passes.
Your job is to CHECK the Phase 5→6 gate, SPAWN review agents in 2 parallel waves, PERFORM 2 consistency checks (CC1, CC2) between waves, ENFORCE the completion quality gate, and optionally TRIGGER PDF generation.
The rtl-p6-design-review-policy skill (loaded via skills: field) defines all review criteria, design note requirements, consistency check protocol, PDF generation pipeline, escalation rules, and the 25-item checklist.
Workflow
Step 0: Context Bootstrap (MANDATORY)
Project root: resolve all project-relative paths (including .rat/...) via the first available of:
explicit PROJECT_ROOT=<abs> line in your spawning prompt > project_root field in .rat/state/spawn-context.json (authoritative when present) > $RAT_PROJECT_ROOT env > process CWD (legacy default).
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.
- 11d ago First seen · 194 lines · 48 tokens per session scan A 5ef6a7ecd1b6
p6-review-orchestrator is an agent published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 18d ago), licensed MIT. It adds 48 tokens to every session and 2,350 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 2026-08-30.
Other agents, from other repositories
diagram-architect
Architecture diagram specialist. Analyzes code and infrastructure to generate Mermaid diagrams, validates business rules, and detects inconsistencies.
visual-qa-agent
Visual QA: screenshot analysis, wireframe comparison, regression detection. Usar PROACTIVELY cuando se detectan cambios en componentes UI o se ejecutan tests E2E.
user-perspective-critic
A product-focused critic that examines a feature from the user's point of view. It reads product rules and test research to ask whether the solution covers real user needs, including spoken Russian input when relevant.
design-handoff-builder
An agent that prepares a structured design brief for Claude Design, a separate tool for creating interface designs. It does not draw the interface itself; the user takes the brief to Claude Design and brings the result back.
prototype-builder
An agent that builds a small clickable HTML/CSS prototype from product requirements and user stories. It uses mock data instead of a backend so the main user flow can be tried before production code is written.
frontend-ux-reviewer
A read-only reviewer that checks new screens, components, layouts, and interactions from the viewpoint of real users.