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-p4s-unit-test-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-p4s-unit-test-policy)<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/rtl-p4s-unit-test-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-p4s-unit-test-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-p4s-unit-test-policy"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-p4s-unit-test-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 | $0.00026 | $0.01983 |
| Opus 5.5 | $0.00010 | $0.00793 |
| Sonnet 5.5 | $0.00005 | $0.00397 |
| Haiku 4.5 | $0.00003 | $0.00198 |
Grade A, and why
rtl-p4s-unit-test-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 15d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tier 2 Unit Test Policy
Coding Convention Requirements
Testbenches MUST follow project conventions:
- Port connections:
i_prefix for inputs,o_prefix for outputs,io_for bidirectional - Clock:
clk(single domain) or{domain}_clk(multiple, e.g.,sys_clk) — NOTclk_i - Reset:
rst_n(single domain) or{domain}_rst_n(multiple, e.g.,sys_rst_n) — NOTrst_ni - Use
logiconly (NOTreg/wire) - DUT instance:
u_prefix (e.g.,u_dut) - Testbench filename:
tb_{module}.sv
Execution Policy
- testbench-dev writes SV testbenches per module (parallel), targeting uarch features
- Reference model comparison: Mode A (DPI-C) or Mode B (file compare) — auto-selected
- func-verifier runs simulations via run_sim.sh and reports results
- Failing tests trigger waveform analysis before reporting
- Gate: all unit tests pass AND reference comparison has zero mismatches
Reference Comparison Modes
| Mode | Condition | Method |
|---|---|---|
| A: DPI-C | refc/build/lib{module}_ref.so exists |
SV TB calls ref functions via DPI-C, cycle-level comparison |
| B: File | DPI-C unavailable | RTL sim → output file, ref binary → output file, diff comparison |
DPI-C setup:
cd refc && mkdir -p build
gcc -std=c11 -shared -fPIC -o build/lib{module}_ref.so src/{module}_ref.c
Result JSON Schema
Each feature entry supports an optional ac_ids field for acceptance criteria traceability:
ac_ids: array of AC IDs covered by this test (e.g.,["REQ-U-012.AC-1", "REQ-U-012.AC-2"])- When the requirement has
acceptance_criteria(structured object array withac_idfields) iniron-requirements.json,ac_idsMUST be populated for each covered criterion. - When
acceptance_criteriais absent or an empty array[],ac_idsmay be omitted (backward compatible).
{
"module": "{module}",
"tier": 2,
"ref_mode": "A_DPI" | "B_FILE",
"features": [
{"name": "fsm_idle_to_active", "status": "PASS", "req_ids": ["REQ-U-003"], "ac_ids": ["REQ-U-003.AC-1"]},
{"name": "pipeline_latency_3cyc", "status": "PASS", "req_ids": ["REQ-U-007"], "ac_ids": ["REQ-U-007.AC-1", "REQ-U-007.AC-2"]},
{"name": "valid_ready_handshake", "status": "PASS", "req_ids": ["REQ-U-012"], "ac_ids": ["REQ-U-012.AC-1"]},
{"name": "transform_accuracy", "status": "FAIL", "mismatch_cycle": 47, "req_ids": ["REQ-U-015"]}
],
"ref_mismatches": 0,
"pass_count": 5,
"fail_count": 0,
"total": 5,
"gap_fill_round": {
"executed": true,
"before": {"line_pct": 52.1, "fsm_pct": 40.0},
"after": {"line_pct": 67.3, "fsm_pct": 55.0}
},
// When gap-fill NOT triggered: {"executed": false, "before": null, "after": null}
"coverage": {
"line_pct": 67.3,
"fsm_pct": 55.0,
"toggle_pct": 42.1
},
"func_coverage": {
"covergroups_defined": 2,
"bins_hit": 14,
"bins_total": 20
},
"codec_conformance": "PASS" | "FAIL" | "N/A"
}
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.
- 15d ago First seen · 161 lines · 26 tokens per session scan A 994d4e7f1679
rtl-p4s-unit-test-policy is a skill published in the GitHub repository babyworm/rtl-agent-team (61 stars, last pushed 16d ago), licensed MIT. It adds 26 tokens to every session and 1,983 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
test-sqrl
Use when adding or updating tests for a DataSQRL pipeline. Use after implementing features to verify correctness.
embedded-testing-patterns
Firmware test patterns with Unity, CMock, Ceedling, and QEMU: project layout, testable HAL interfaces, CMock expect chaining, error-path tests, and an on-target test runner over ITM. Use when making embedded C testable or writing tests for it.
mavlink-integration
Use this skill when a task involves MAVLink protocol communication via pymavlink, UART/UDP/TCP drone connections, ArduPilot SITL simulation, or telemetry message parsing in the edge service. Don't use it for raw UART hardware driver code without MAVLink framing (use embedded-systems), WebSocket transport to the web…
codexkit-test-hardening
Strengthen test coverage around changed behavior, edge cases, and regressions without writing noisy or brittle tests.
testing-business-rules
Use when adding, reviewing, or deleting tests, deciding whether a function needs coverage, or when a suite enumerates branches, signs, empty values, or implementation steps without naming the behavior at risk.
precommit
Run the deterministic pre-commit pipeline in fast or full mode through the packaged runner. Use when handing off repository changes. Not for: ad hoc replacement checks, dependency audits, or read-only verification. Output: runner-owned changed-file reporting and final verdict.