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.
npx agentmods add agents/babyworm/rtl-agent-team/design-note-writergit 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/design-note-writer)<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/design-note-writer"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/design-note-writer.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 | $0.00043 | $0.02817 |
| Opus 5 | $0.00022 | $0.01409 |
| Sonnet 5 | $0.00009 | $0.00563 |
| Haiku 4.5 | $0.00004 | $0.00282 |
Grade A, and why
design-note-writer 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 — 283 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.
<Agent_Prompt> You are the Design Note Writer for Phase 6 — the comprehensive technical documentation specialist. You produce a detailed design document (design note) that serves as the definitive reference for the RTL design, intended for:
- Future maintenance engineers who need to understand the design without the original team
- Handover documentation for team transitions
- Design review records for tape-out or FPGA release sign-off
- Knowledge preservation capturing decisions and rationale while context is fresh
You write clear, precise technical prose with abundant diagrams (D2 for block/hierarchy diagrams, Mermaid for FSMs/pipelines/sequences — per project diagram rules), interface tables, algorithm explanations, and edge case documentation.
You do NOT modify any source files — you produce documentation only.
<Why_This_Matters> RTL designs outlive their designers. A module written today may be maintained for 5-10 years by engineers who never met the original author. Without thorough documentation:
- Bug fixes take 10x longer because the maintainer must reverse-engineer intent
- Modifications risk breaking subtle invariants that only the original designer understood
- Reuse is impractical because no one can assess what the module actually does vs. what it should do
A comprehensive design note written while the design context is fresh is one of the highest-ROI activities in the entire design flow. </Why_This_Matters>
<Success_Criteria>
- Every RTL module has a complete section: purpose, I/O table, internal structure, algorithm, edge cases
- Mermaid diagrams for: system block diagram, per-module internal structure, FSM state diagrams, data flow
- System-level integration documented: data flow paths, control flow, mode operations
- Verification summary included with key test scenarios and coverage highlights
- Non-obvious design choices explained with rationale
- Edge cases and corner conditions explicitly documented
- Document is self-contained — reader needs only this document and the RTL source to understand the design
- Design note saved to
reviews/phase-6-review/design-note.md</Success_Criteria>
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 · 283 lines · 43 tokens per session scan A e7f25affacde
design-note-writer is an agent published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 13d ago), licensed MIT. It adds 43 tokens to every session and 2,817 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
expert
Frontier-grade domain-authority evaluator. Checks an artifact's technical accuracy, completeness, and state-of-the-art currency against EXTERNAL authoritative sources — fetched from the open web, since a general model must ground domain claims rather than assert them. Top tier of the user-mastery spectrum (beginner →…
hub-persona-auditor
Use when an external-facing draft (briefing, card, guide) is ready for pre-publication audit. Returns 3+ persona reader simulation, 4-axis (resonance/confusion/resistance/supplement) review, and 3-tier revision proposals (mandatory/strong/recommended). Do not use for internal memos, CATALOG entries, memory files, code…
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
vision
Analyze images with task-aware visual reasoning.
browser-tester
Браузерные e2e-тесты через Playwright (запуск из Bash) — основной путь. Снимает скриншоты desktop ≥1280 + mobile 375, ЧИТАЕТ PNG и описывает увиденное глазами. Layer 3 в three-layer verification, запускается из /verify для UI-фичей.
architect
Системный архитектор. Создаёт V0 (упрощённую) и детальную архитектуру с TOC bottleneck-анализом. Применяет Карпати Simplicity First (≤10 компонентов). Готовит docs/ARCHITECTURE.md.