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 rtl-p5s-func-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/rtl-p5s-func-verify-policy)<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/rtl-p5s-func-verify-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-p5s-func-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/rtl-p5s-func-verify-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-p5s-func-verify-policy.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 | $0.00028 | $0.02772 |
| Opus 5.5 | $0.00011 | $0.01109 |
| Sonnet 5.5 | $0.00006 | $0.00554 |
| Haiku 4.5 | $0.00003 | $0.00277 |
Grade A, and why
rtl-p5s-func-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 20d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tier 3 Functional Verification Policy
Testing Tier Context
Tier 1: Smoke Test — connectivity, R/W, basic ops (rtl-p4-implement Wave 4)
Tier 2: Unit Test — reference comparison, uarch features (rtl-p4s-unit-test)
Tier 3: Module Regr. — cocotb multi-seed (THIS POLICY)
Tier 4: Integration — cross-module, end-to-end (rtl-p5s-integration-test)
Tier transition rules:
- Tier 2 PASS (rtl-p4s-unit-test) → Tier 3 eligible
- Tier 3 PASS or PARTIAL_PASS (this skill) → Tier 4 eligible (rtl-p5s-integration-test) (PARTIAL_PASS = some Critical/High ac_ids PARTIAL; WARNING at Stage 1, escalated to FAIL at Stage 3)
- Tier 3 FAIL → fix via rtl-p4s-bugfix, re-run Tier 2 then Tier 3
cocotb Signal Naming Convention
cocotb test files MUST use correct signal names matching RTL port conventions:
- Signal access:
dut.i_data(NOTdut.data_i),dut.o_valid(NOTdut.valid_o) - Clock:
dut.clk(single domain) ordut.sys_clk(multiple domains) — NOTdut.clk_i - Reset:
dut.rst_n(single domain) ordut.sys_rst_n(multiple domains) — NOTdut.rst_ni - cocotb clock utility:
cocotb.clock.Clock(dut.sys_clk, 10, units="ns") - Reset sequence: drive
dut.sys_rst_n.value = 0, wait, thendut.sys_rst_n.value = 1
Multi-Seed Strategy
- Default 5 seeds: 1, 42, 123, 1337, 65536 (configurable via
sim/regression/seed_list.txt) - Each seed tests different random stimulus ordering
- A module passes multi-seed regression only when ALL seeds pass
- Use
COCOTB_RESOLVE_X=RANDOMfor X-state handling - Use
RANDOM_SEED={seed}for reproducibility
Execution Strategy
- Local-first runtime: default to local execution on current host (
--mode local) - Default parallel budget: use
max(1, nproc-2)unless user explicitly overrides--parallel - AWS usage policy:
aws-batchis allowed only when the user explicitly asks to use AWS and explicit gate/runner wiring exists (RTL_ALLOW_AWS=1,RTL_AWS_BATCH_RUNNER) - Pipelined: as each module's TB completes → immediately launch sim (don't wait for all TBs)
- Module-level parallelism: each module's TB + sim runs as an independent parallel task
- Multi-seed parallelism: queue 5 seeds × N modules; local active workers stay within
max(1, nproc-2) - Incremental coverage: coverage-analyst starts partial analysis on completed modules
- Early termination: >5% failure rate across seeds → halt and report immediately
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.
- 20d ago First seen · 221 lines · 28 tokens per session scan A e22a7ca4d8fe
rtl-p5s-func-verify-policy is a skill published in the GitHub repository babyworm/rtl-agent-team (61 stars, last pushed 21d ago), licensed MIT. It adds 28 tokens to every session and 2,772 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
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.
visual-acceptance
A visual final-review method for user-interface changes. It checks the rendered result with repeatable screenshots, pixel values, computed styles, and CSS layering checks across themes.
verification-strategy
Thorough verification of completed work before declaring done.
local-test
Build, run, and test IronClaw locally using Docker containers and Chrome MCP browser automation.
qemu-kernel-build
Use for building Linux kernels for QEMU boot testing, including defconfig selection, cross compile variables, Docker or host toolchains, Image, DTB, modules, initramfs inputs, output hashes, and provenance records.