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 agentmods add skills/vibeic/vibe-ic/hw-debug-loopnpx skills add vibeic/vibe-ic --skill hw-debug-loopgit clone --depth 1 https://github.com/vibeic/vibe-icWrote 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/vibeic/vibe-ic/hw-debug-loop)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/hw-debug-loop"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/hw-debug-loop.svg" alt="Measured on agentmods" 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 | $0.00191 | $0.02981 |
| Opus 5 | $0.00096 | $0.01491 |
| Sonnet 5 | $0.00038 | $0.00596 |
| Haiku 4.5 | $0.00019 | $0.00298 |
Grade A, and why
hw-debug-loop 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 4d 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Case-study notation. This skill cites the / / MDV-A1101 reference project as concrete evidence for the rules below. The rules themselves are chip-AGNOSTIC and apply to any IC of the matching
ic_class(seevibe-ic-marketplace/plugins/vibe-ic/programs/ic_class_profile.py). When you adopt this skill on a different IC, swap<chip-class>→<your IC name>and<half-duplex-tester>→<your host-tester name>; the structural gates and rule bodies do not depend on those SKUs. Seedocs/design/CASE_STUDIES/AS3616_*.mdfor the full regression history.
Closed Hardware Debug Loop
Phase 2c, post-burn: the plugin's structural gates have all PASSed,
the project's BFM is 12/12 byte-exact, the SOF is burned, but the host
acceptance test (the project's <host_tester> verdict — e.g. byte[6]
on a half-duplex protocol IC, or the equivalent rig verdict for the
target IC class) FAILs. This skill is the methodology that drives the
fix without an indefinite trial-and-error loop.
Why This Skill Exists
After v0.119.5–v0.119.11 the plugin captures Categories A and most of C. Two classes of failure remain:
-
Category B — vendor doc disagrees with silicon (e.g. v099 oracle returns 18 bytes for 0xE6 but the doc says 22). Plugin extractor cannot detect this from L1-L27 alone; the only ground truth is silicon.
-
Category C residual — sub-microsecond pad / FPGA-pad-inference details that surface only when a particular agent's RTL pattern interacts with a particular silicon's analog front-end. Each new instance becomes a new structural gate (LL-15/16/17/23 are these), but the next one is unknown until it appears.
The closed debug loop converts an indefinite "try-and-error until it works" into a bounded sequence of named experiments, each producing a named evidence file, each leading to a deterministic next step.
When to Use
What ships with it
2 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.
- 4d ago First seen · 268 lines · 191 tokens per session scan A ba20bfaa9df8
hw-debug-loop is a skill published in the GitHub repository vibeic/vibe-ic (21 stars, last pushed today), licensed Apache-2.0. It adds 191 tokens to every session and 2,981 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
analog-netlist-crawl
Crawl and analyze post-layout parasitic netlists without running SPICE. Answers "what's the effective resistance from node A to node B across this massive R mesh?", "inside the VREFN mesh, which device pins are electrically farthest apart?", "which nets have the worst coupling?", "where does settling bottleneck?" — by…
analog-verify
Pre-simulation review and Spectre simulation verification for analog circuits. Reviews circuit netlist and testbench, runs simulation, produces margin report. Use after analog-design completes a netlist.
analog-design
Transistor-level circuit design for one analog sub-block. Produces Spectre netlist with hand-calculation rationale. Use when designing a specific circuit block after architecture is defined.
analog-pipeline
MANDATORY — MUST load this skill when the user mentions: OTA, ADC, PLL, comparator, bandgap, LDO, amplifier, opamp, or any analog/mixed-signal IC design task. Full analog design pipeline: spec -> architecture -> design -> verify -> deliver. Orchestrates analog-decompose, analog-behavioral, analog-design…
analog-audit
Audit analog circuit netlists for correctness, quality, and risks. Supports both pre-layout (schematic) and post-layout (extracted) netlists. Post-layout mode filters massive parasitic netlists before auditing. Works without EDA. TRIGGER on: "audit", "review netlist", "check this circuit", "design review"…
analog-evolve
Self-evolution engine for analog-agents. Reviews completed design sessions to extract lessons, discover new anti-patterns, propose checklist additions, and refine agent prompts. Run after design convergence or project completion. TRIGGER on: "evolve", "what did we learn", "improve skills", "meta-review"…