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-integration-testgit 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-integration-test)<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/rtl-p5s-integration-test"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-p5s-integration-test/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-integration-test"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-p5s-integration-test.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 | $0.00042 | $0.01756 |
| Opus 5.5 | $0.00017 | $0.00702 |
| Sonnet 5.5 | $0.00008 | $0.00351 |
| Haiku 4.5 | $0.00004 | $0.00176 |
Grade A, and why
rtl-p5s-integration-test 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- All modules pass Tier 2 unit tests and Tier 3 module regression (PASS or PARTIAL_PASS).
- Cross-module interactions need verification (interface mismatches, protocol handshakes).
- Phase 5 integration verification step is required.
- Multi-module RTL changes may have affected interface compatibility. </Use_When>
<Do_Not_Use_When>
- Individual modules still fail Tier 2 unit tests — fix at Tier 2 first.
- Only single-module regression is needed — use
rtl-p5s-func-verify(Tier 3). - Performance measurement is the goal — use
rtl-p5s-perf-verify. - Standards conformance bitexact testing is needed — use
rtl-conformance-test. </Do_Not_Use_When>
<Why_This_Exists> Modules that pass individually may fail when connected due to interface mismatches, protocol violations, or timing assumptions that do not hold across boundaries. Integration testing catches: port width mismatches, reset not propagating to all sub-modules, backpressure not flowing through the pipeline, and data corruption at handoff points. These bugs are invisible to per-module testing. </Why_This_Exists>
Prerequisites
- All modules pass Tier 2 (
rtl-p4s-unit-test) and Tier 3 (rtl-p5s-func-verify) — PASS or PARTIAL_PASS. - RTL source files exist under
rtl/**/*.sv. - Phase 2 refC model output available as end-to-end reference oracle.
If prerequisites are missing: WARNING — recommend completing Tier 2 and Tier 3 first. Orchestrator adapts scope with available artifacts.
<Responsibility_Boundary>
- Scripts handle deterministic checks: static connectivity analysis (port width/direction mismatches at module boundaries) before dynamic simulation is run.
- LLM handles interpretive analysis: handshake protocol observation, reset propagation verification narrative, and end-to-end reference comparison result interpretation.
- Contract surface:
integration_results.jsonschema and test categories documented inreferences/integration-test-conventions.md. </Responsibility_Boundary>
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/dut_top_connectivity.json 989 B
- examples/dut_top.sv 1009 B
- examples/pixel_gen.sv 568 B
- examples/pixel_pack.sv 945 B
- examples/README.md 2.2 KB
- references/.gitkeep 0 B
- references/integration-test-conventions.md 3.5 KB
- scripts/.gitkeep 0 B
- scripts/check_connectivity.py 31 KB runs code
- templates/integration-tb-template.sv 5.8 KB
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 · 115 lines · 42 tokens per session scan A 99e57712d0d0
rtl-p5s-integration-test is a skill published in the GitHub repository babyworm/rtl-agent-team (57 stars, last pushed 9d ago), licensed MIT. It adds 42 tokens to every session and 1,756 once invoked, about $0.0002 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
jetson-video-pipeline
Use when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or concise acceptance workflows.
image-compare
Compare two image files on disk and report what changed, region by region. Trigger on "what changed between these two images", "diff these PNGs", "did this render drift", "compare screenshots/exports/renders".
local-test
Build, run, and test IronClaw locally using Docker containers and Chrome MCP browser automation.
browser-qa
Drive a real headless browser against a locally-served web UI and capture screenshot evidence, reporting step-level PASS/FAIL/BLOCKED with extracted DOM text and console errors. Use when a phase on the docker QA image must exercise a rendered UI and attach screenshots — it complements the text-evidence verify/qa-test…
qa-test
Run an automated QA flow against a CLI or a locally-served app and report step-level pass/fail with evidence. Use when asked to QA-test a feature, exercise a flow end-to-end, or smoke-test what a PR changed.
qp
QP (Quality Platform) router — takes a web URL or a desktop app name and runs the plan → run → regress loop (qp-plan, qp-run, qp-regress) end to end, or routes to one stage. Classifies the target (public vs profile-required), probes which adapter the session has (Playwright MCP for web, computer-use MCP for desktop)…