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-bug-reprogit 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-bug-repro)<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/rtl-bug-repro"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-bug-repro/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-bug-repro"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-bug-repro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Memory Poisoning · line 57 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00038 | $0.01928 |
| Opus 5 | $0.00019 | $0.00964 |
| Sonnet 5 | $0.00008 | $0.00386 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade A, and why
rtl-bug-repro 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- A bug has been reported with a failure log or a failing test case.
- A simulation failure needs root cause analysis before an RTL fix is attempted.
- A regression failure needs isolation to a specific module. </Use_When>
<Do_Not_Use_When>
- The bug is in the testbench, not in RTL — fix the testbench directly.
- The root cause is already known — proceed to RTL fix.
- The bug is a synthesis issue — use
rtl-synth-checkinstead. </Do_Not_Use_When>
<Why_This_Exists>
Debugging without a minimal reproduction wastes time. Waveform analysis on the full regression is slow; a targeted minimal TB isolates the failure in minutes. root_cause.md documents the finding for the RTL engineer making the fix, and the repro TB can be added directly to the regression suite.
</Why_This_Exists>
Prerequisites
- A failure log or failing
.vcd/.fstwaveform from a previous simulation run. - RTL source for the suspected module under
rtl/**/*.sv.
If prerequisites are missing: WARNING — recommend running the failing regression test first to obtain a waveform. Proceed with available artifacts; the orchestrator adapts scope.
<Responsibility_Boundary>
- Scripts handle deterministic waveform work:
vcd_diff.pyidentifies the exact divergence cycle and signal path between two VCD files. - LLM handles interpretive content: root cause hypothesis, signal trace narrative, suspected RTL location, and minimal stimulus design.
- Contract surface:
root_cause.mdstructure documented inreferences/bug-repro-conventions.md. </Responsibility_Boundary>
Apply steps 1-6 to every bug ID requested — do not stop after the first.
<Tool_Usage> Waveform analysis (when no golden VCD for diff):
Task(subagent_type="rtl-agent-team:waveform-analyzer",
prompt="Analyze sim/regression/test_cabac_fail.vcd. Find first divergence between actual and expected output. Identify originating module and signal path. Port signals use i_/o_ prefixes, clocks are {domain}_clk, resets are {domain}_rst_n.")
What ships with it
8 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.
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 · 117 lines · 38 tokens per session scan A 433b927b311f
rtl-bug-repro is a skill published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 18d ago), licensed MIT. It adds 38 tokens to every session and 1,928 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
hardware-health-check
Out-of-band hardware health via Redfish BMC (read-only) — power state, component health, thermal and power readings, firmware inventory, SEL log triage. Use when determining whether a host is powered off versus unreachable, checking hardware faults, reviewing thermal or PSU state, or triaging BMC event logs.
boot-doctor-mcp
Deterministic PC no-boot / no-POST / no-display troubleshooting — real BIOS beep-code lookup and a ranked next-steps engine, no LLM guessing at hardware causes. Use this whenever the user describes a computer that won't turn on, won't POST, has no display output, is beeping, or asks for hardware troubleshooting steps…
fpga-hardware-design-and-review-guide
Comprehensive FPGA hardware design guide based on real-world project experience. Covers pipeline architecture, timing optimization, SystemVerilog coding patterns, CDC handling, and practical debugging techniques. Use this skill when: (1) designing FPGA modules with timing constraints, (2) implementing video processing…
vdebug
Trace failing signals through the RTL hierarchy, classify root cause, and write a debug report per issue — no fix is proposed.
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…