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 skills add babyworm/rtl-agent-team --skill p2-arch-design-policygit 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/skills/babyworm/rtl-agent-team/p2-arch-design-policy)<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/p2-arch-design-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/p2-arch-design-policy/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/skills/babyworm/rtl-agent-team/p2-arch-design-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/p2-arch-design-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00023 | $0.02584 |
| Opus 5 | $0.00012 | $0.01292 |
| Sonnet 5 | $0.00005 | $0.00517 |
| Haiku 4.5 | $0.00002 | $0.00258 |
Grade A, and why
p2-arch-design-policy 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.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 2 Architecture Design Policy
P1 Algorithm Candidate HW Review Criteria
For each functional area's candidates from P1's domain-analysis.md, evaluate:
- Gate count estimate (from literature or analytical estimation)
- Critical path depth (combinational logic levels)
- SRAM requirements (capacity, banking, port count)
- External memory bandwidth (bytes/pixel, access patterns)
- Achievable throughput at target frequency (pixels/cycle, blocks/cycle)
- Implementation risk (tool support, verification complexity, proven vs novel)
Architecture Review Criteria (Dynamic Convergence Protocol)
Dynamic convergence review (min 2, max 5 rounds), coordinated by rtl-architect:
- 3 mandatory parallel reviewers each round: (a) rtl-architect: spec compliance (Feature Coverage Checklist) + structural review (b) vcodec-architecture-expert: memory access patterns, performance analysis (c) ref-model-dev: architecture ↔ C model consistency (block mapping, data flow, interfaces)
- +1 conditional reviewer: (d) ref-model-reviewer: independent C model quality gate (algorithm fidelity, numerical precision, undefined behavior/build warning risk) when ref model is newly created or substantially revised
- ref-model-reviewer activation threshold: Invoke when ref model is newly created OR
30% of source lines changed from prior version. Both sequential and team orchestrators use this same threshold. Skip review tasks when ref model is unchanged.
- Each round: review → rebuttal (designer accepts/rejects each finding with rationale) → tree exploration for issues → targeted revision (rejections recorded in per-round artifact)
- Last round (converged or max reached): cross-block interface audit + memory conflict analysis
- Convergence check after round >= min_rounds: finding_delta < 0.1, all critical resolved, wonder stable
- After max_rounds if not converged → escalate to user via AskUserQuestion
Architecture Naming Conventions
- Block names:
snake_case(become RTL module names in Phase 4) - Interface descriptions: data width, protocol type, direction — NOT RTL port naming
- RTL naming conventions (i_/o_ prefix, clock/reset naming) applied in Phase 4, not here
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.
- 8d ago First seen · 213 lines · 23 tokens per session scan A 3613e2c8341c
p2-arch-design-policy is a skill published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 18d ago), licensed MIT. It adds 23 tokens to every session and 2,584 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
qa-review
QA review for code changes — test coverage analysis, edge case identification, test plan generation, regression detection, test health tracking over time.
readable-verilog-generator
Use when creating, writing, reviewing, annotating, repairing, refactoring, or validating readable Verilog RTL, including synthesizable Verilog-2001 .v files, existing-RTL analysis, semantic comment annotation, testbench scaffold planning, ASIC-quality review, local or remote Vivado/xsim validation, evidence-backed…
aster-review-ci
Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.
fresh-eyes-loop
A repeatable quality-review process using two independent agents: one reviews and verifies, while the other fixes issues. P0 and P1 mean the highest-severity problem levels.
kicad-pcb-review
Use this skill when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.
rtl-review
Audit RTL code for lint violations, synthesis hazards, coding-style compliance, and readability. Use when the user says "review this Verilog", "check my RTL", "lint this module", "is this code synthesizable", or shares an HDL file and asks for feedback before simulation or tape-in.