Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeic/vibe-icnpx agentmods add skills/vibeic/vibe-ic/phase2-rtl-verifyWrote 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/phase2-rtl-verify)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/phase2-rtl-verify"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/phase2-rtl-verify/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/vibeic/vibe-ic/phase2-rtl-verify"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/phase2-rtl-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.02317 |
| Opus 5 | $0.00039 | $0.01158 |
| Sonnet 5 | $0.00016 | $0.00463 |
| Haiku 4.5 | $0.00008 | $0.00232 |
Grade A, and why
phase2-rtl-verify 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 6d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 2 RTL Verification
Doctrine (v0.1.50): 把修法寫進工具，而非寫進 prompt. Programs first; AI is the backstop on residual narrative.
Mandatory Deterministic Preflight
python3 plugins/vibe-ic/programs/phase2_verify_aggregate.py \
<project_dir> \
--out-md /tmp/phase2_verify.md \
--out-json /tmp/phase2_verify.json --strict
The aggregator runs rtl_precheck_gate, spec_conformance_check, and
rtl_hygiene_lint, AND checks RTL/SOF/TB artifact presence. Refuse
to claim Phase 2 PASS without the aggregator's verdict: PASS.
How you are invoked: the stage-1 ON-PASS review
This skill is the AI half of stage1.on_pass_review in
flow/phase1_phase2_phase3.yaml — the flow's ONE declaration of it. Until that
block existed, this skill (and the other seven in the verification tier)
appeared ZERO times in the flow: every skills: array there hangs on a FAILURE
trigger, so the AI was wired as an author and as a repairer and never as a
reviewer of a program that PASSED.
Order, and it is not negotiable:
-
The program runs first.
design_one_shot_runnerproduces the stage-1 artefact; the stage's gates pass. -
The deterministic on-pass rung runs next.
python3 programs/stage_on_pass_review.py <project> --stage stage1 \ --compliance reports/audit/flow_compliance.json \ --json reports/phase2/gates/stage1_on_pass_review.jsonIt reads the INTENT (
phase1/generated_docs/L9_INTEGRATION_SPEC.json) and the ARTEFACT (phase2/stage1/rtl/,reports/phase2/). Exit 0 = ACCEPT, 1 = REJECT with evidence, 2 = NOT CHECKED. On a rejection it WRITES the run's own regression underreports/phase2/gates/on_pass_review/— a test that FAILS on this run and passes when it is repaired. -
You take what is left. Everything the program ACCEPTED or reported as
NOT CHECKEDis your input, not your conclusion. Read its--jsonrecord first:rules[]says which contract was decided deterministically, so you do not re-derive it and do not contradict it without new evidence.
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.
- 6d ago First seen · 160 lines · 78 tokens per session scan A 5a96dd8fc0fc
phase2-rtl-verify is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 78 tokens to every session and 2,317 once invoked, about $0.0004 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
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.
boardrepo
Read and review real PCB projects on BoardRepo. Search published hardware designs, open a board's schematic connectivity, bill of materials and files, run KiCad's DRC and ERC, and check a design against a fabrication house's limits. Use whenever the user names a BoardRepo board or URL, asks to find a published board…
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-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"…