Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add vibeic/vibe-ic/plugin install 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/commands/vibeic/vibe-ic/vibe-ic-phase3)<a href="https://agentmods.dev/commands/vibeic/vibe-ic/vibe-ic-phase3"><img src="https://agentmods.dev/badge/commands/vibeic/vibe-ic/vibe-ic-phase3/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/commands/vibeic/vibe-ic/vibe-ic-phase3"><img src="https://agentmods.dev/badge/commands/vibeic/vibe-ic/vibe-ic-phase3.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 | $0.01020 |
| Opus 5 | $0.00021 | $0.00510 |
| Sonnet 5 | $0.00008 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
vibe-ic-phase3 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 10d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Missing arg? When
$ARGUMENTSis empty, prompt the user first:/vibe-ic-phase3 <project-dir>(e.g./vibe-ic-phase3 1st_benchmark_example/phase2_v0119.48-vendor). The AI must NOT guess the path; a concrete project path is required before continuing.
/phase3 — Phase 3 (silicon backend)
Prerequisite: at least one of <project>/rtl/*.sv and <project>/input/pdk/{liberty,lef}/ is present (PDK can be auto-detected or fall back to sky130A). /phase2 complete is best.
Main execution (program-driven):
python3 ${CLAUDE_PLUGIN_ROOT}/programs/phase3_one_shot_runner.py $ARGUMENTS
The runner automatically:
- PDK detect (input/pdk/liberty + lef → custom; fallback sky130A)
- macro detect (input/pdk_local//{lib,LEF,PA_GDS,Verilog})
- Calibre / Assura DRC + LVS deck detect
- yosys synth (macro libs as blackbox)
- OpenROAD floorplan + place + CTS + global_route → DEF + sta.rpt
- KLayout DEF→GDS (merge macro PA-GDS)
- KLayout DRC (when .lydrc or deck is available)
- Netgen LVS (when reference netlist is available)
After the run completes, the AI must:
- Read
<project>/reports/phase3_one_shot.jsonand inspect the verdict - For every FAIL step:
synthFAIL → checkphase3/synth/synth.log; common: vendor primitive missing black-box (need to add macroread_liberty -lib),SIMULATIONdefine not effective (runner already set),assertions.svleaking into synth (runner already filters)pnrFAIL → checkphase3/pnr/openroad.log; common: site name detected wrong, metal_prefix detected wrong, CTS buffer not in liberty, die size too small (util > 80% requires enlarging die), missing TRACKS (runner already addsmake_tracks), SDC ref FPGA-only port → close-loop fix_detect_pdkheuristicgdsFAIL → check KLayout stream-out log; usually LEF conflict (multiple LEF variants for the same macro) → fixlef_by_macroselection logicdrc/lvsWAIVED is legal (commercial deck must be run offline); but if .lydrc should exist yet was not found, hint to fix the path
- All PASS / PASS_WITH_WAIVERS → hint: tapeout review
Helper skills: synthesis-driver / pnr-orchestrate / drc-orchestrate / lvs-orchestrate / gds-export / tapeout-checklist
Rule: Phase 3 PASS requires synth + pnr + gds all PASS (DRC/LVS may be WAIVED → must be run offline for sign-off before tapeout).
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.
- 10d ago First seen · 50 lines · 42 tokens per session scan A 02f620193772
vibe-ic-phase3 is a command published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 1,020 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 2026-08-30.
Other commands, from other repositories
pcb-new
Start a new PCB project from a text description. Sources parts, generates a wired .kicadpcb, and hands off to EasyEDA for routing + JLCPCB ordering.
pcb-from-bom
Start a PCB project from an existing LCSC BOM file (CSV with C-numbers) and a design-intent description.
gf-cocotb
Generate Python testbench using Cocotb.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.