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 rat-p4p5-impl-verify-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/rat-p4p5-impl-verify-policy)<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/rat-p4p5-impl-verify-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rat-p4p5-impl-verify-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/rat-p4p5-impl-verify-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rat-p4p5-impl-verify-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 | $0.00030 | $0.02386 |
| Opus 5 | $0.00015 | $0.01193 |
| Sonnet 5 | $0.00006 | $0.00477 |
| Haiku 4.5 | $0.00003 | $0.00239 |
Grade A, and why
rat-p4p5-impl-verify-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 7d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
μArch-to-Verify Policy
Core Principles
Hierarchical Spec Compliance
Lower phases MUST NOT violate upper phase specifications: Spec → Architecture → μArch → RTL → Verification RTL must faithfully implement the μArch design. Verification must validate against the original Spec.
Design Priority Order
- Functional Correctness (highest) — Every required feature works exactly
- Interface Compliance — Ports, protocols, timing match Architecture
- Timing/Performance — Throughput, latency targets met
- Area/Power (lowest)
Document-as-Memory
Phase 4 reads Phase 1-3 documents as input context. Phase 5 reads Phase 4 artifacts.
No agent needs to "remember" another agent's output — it reads the document.
State is persisted at .rat/state/rat-p4p5-impl-verify-state.json for resumability.
Execution Rules
Dual-Layer Phase Gates
Phase 4→5 transition requires BOTH:
- Artifact Gate: Required files exist (fast check)
- Quality Gate: Reviewer agent(s) verify quality AND hierarchical spec compliance
Quality Gate verdicts: PASS or FAIL + findings[]
Gate Retry Policy
- Artifact Gate failure: retry phase once, then escalate to user
- Quality Gate failure: pass findings to worker agent, re-run gate. Max 2 retries
- Upper-spec violation: IMMEDIATE STOP (see Escalation)
Context Preload
Before each phase, verify required upstream files exist:
- required (full read): files that MUST be fully read before starting the phase
- summary only: files where only the phase summary is sufficient
- optional (on demand): files read only when a specific question arises
Specific file lists are defined inline in each orchestrator's phase steps.
Termination
After Phase 5 Final Compliance Gate PASS, generate summary, then STOP. Do NOT proceed to Phase 6.
Prerequisite Requirements
| Artifact | Required Check |
|---|---|
docs/phase-3-uarch/*.md |
At least one μArch module spec exists |
reviews/phase-3-uarch/uarch-review.md |
File exists AND contains Verdict: PASS |
docs/phase-1-research/iron-requirements.json |
File exists (needed for traceability) |
docs/phase-1-research/io_definition.json |
File exists (needed for port verification) |
refc/*/*.c |
At least one C reference model source exists |
docs/phase-3-uarch/phase-3-summary.md |
File exists (Phase 3 summary for context) |
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.
- 7d ago First seen · 201 lines · 30 tokens per session scan A 256776c7f608
rat-p4p5-impl-verify-policy is a skill published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 18d ago), licensed MIT. It adds 30 tokens to every session and 2,386 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 2026-09-03.
Other skills, from other repositories
tuyaopen/usr-board
A workflow for adding a custom peripheral to a TuyaOpen project without changing the software development kit. A peripheral is an attached hardware device, and a TDD is a hardware driver interface used to control it.
vtestgen
Scaffold a Makefile-driven, CPU-bus-controlled testbench project for an IP and generate a comprehensive set of self-checking testcases, validate each with make, and write a testcase list.
vtestrun
Run all IP-level testcases from tclist.md through the bench Makefile, capture results, and write per-failure issue reports with no fix suggestions.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
holohub-app-lifecycle
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.