vibe-ic-phase2

vibe-ic-phase2 is a command for Claude Code from vibeic/vibe-ic. It costs 55 tokens per session (1,086 once invoked), scanned A, original, Apache-2.0.

A command that runs Phase 2 of a hardware design workflow: generating and checking RTL, compiling it for an FPGA, programming the board, and verifying it on the device. RTL is code that describes digital hardware.

In plain words
What is it for?
Use it on a project containing the required Phase 1 JSON files to run design generation, simulation, synthesis, FPGA compilation, board programming, on-board verification, and final auditing.
Why use it?
It automates the ordered checks needed to move from generated design documents to a tested FPGA result and reports which step failed.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the vibe-ic plugin — 70 skills, 8 commands, 8 agents, 2 hooks, 1 MCP server shipped together

Good fit Use it on a project containing the required Phase 1 JSON files to run design generation, simulation, synthesis, FPGA compilation, board programming, on-board verification, and final auditing.

Compare 6 commands from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add vibeic/vibe-ic
Claude Code
/plugin install vibe-ic

Made for: Claude Code.

Or install vibe-ic, the plugin that ships this one along with the rest of its 70 skills, 8 commands, 8 agents, 2 hooks, 1 MCP server.

Wrote 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.

agentmods badge for vibe-ic-phase2

README.md
[![agentmods](https://agentmods.dev/badge/commands/vibeic/vibe-ic/vibe-ic-phase2/github.svg)](https://agentmods.dev/commands/vibeic/vibe-ic/vibe-ic-phase2)
Your own site
<a href="https://agentmods.dev/commands/vibeic/vibe-ic/vibe-ic-phase2"><img src="https://agentmods.dev/badge/commands/vibeic/vibe-ic/vibe-ic-phase2/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.

agentmods 80×15 button for vibe-ic-phase2

Your own site · 80×15
<a href="https://agentmods.dev/commands/vibeic/vibe-ic/vibe-ic-phase2"><img src="https://agentmods.dev/badge/commands/vibeic/vibe-ic/vibe-ic-phase2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,086 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.01086
Opus 5 $0.00028 $0.00543
Sonnet 5 $0.00011 $0.00217
Haiku 4.5 $0.00006 $0.00109

Measured 6d ago against content hash af45a4e925ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

vibe-ic-phase2 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.

vibe-ic-marketplace/plugins/vibe-ic/commands/vibe-ic-phase2.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Missing arg? When $ARGUMENTS is empty, prompt the user first: /vibe-ic-phase2 <project-dir> (e.g. /vibe-ic-phase2 1st_benchmark_example/phase2_v0119.48-vendor). The AI must NOT guess the path; a concrete project path is required before continuing.

/phase2 — Phase 2 (RTL → SOF → on-board verify) entry

Prerequisite: <project>/generated_docs/L1..L13.json must exist (produced by /phase1 or /phase1).

Main execution (program-driven):

python3 ${CLAUDE_PLUGIN_ROOT}/programs/design_one_shot_runner.py $ARGUMENTS

The runner runs: rig_topology skeleton → detect_ic_class → rtl_gen → reference_tb → yosys → qsf/sdc → otp_image_check → fpga_compile → fpga_burn → md905_verify → phase2_manifests → final_audit.

After the run completes, the AI must:

  1. Read <project>/reports/phase23_one_shot.json, find the verdict and per-step status
  2. If <project>/phase2/stage1/formal/formal_authoring_request.json exists, invoke formal-verify now on that artifact. This is a required fallback, not a suggestion in a manifest: read every unresolved L3/L6/L8 obligation ID, author only sound properties bound to visible RTL/declarations, update property_contract.json, write formal_expert_review.json with invocation_status: INVOKED and a dispositions list containing one row per obligation (id, status, and the exact property name for every AUTHORED row), then run formal_property_run.py and formal_proof_evidence_check.py. If no sound property can be authored, keep the request verdict: INCOMPLETE and name the missing declaration/property; never replace it with a skip.
  3. For every FAIL step:
    • rtl_gen FAIL → check aid_class_rtl_gen.py stderr; usually L8/L9 fields missing → return to /phase1 to fill in
    • reference_tb FAIL → iverilog parse / sim error; bounded RTL repair/retry loop (runner auto-retries up to 3 times); if retries are exhausted, modify aid_class_rtl_gen.py template
    • fpga_compile FAIL → check fpga/compile.log; common: QSF init_file SEARCH_PATH, SystemVerilog patterns Quartus does not accept → fix RTL template / qsf_gen
    • fpga_burn FAIL → parse error_code and failed_gates (pre-burn structural-gate audit); close-loop each gate (call programs/<gate>.py to capture detail → patch RTL/L doc → re-run)
    • md905_verify FAIL → <unparsed> = driver did not see frame; first verify the SOF was burned in + connected to PIN_V10; if expected ≠ observed it is a real hardware bug and requires RTL repair (not a metal-layer ECO)
  4. All PASS → hint: /phase3

Helper skills: spec-to-rtl / cdc-check / rtl-review / formal-verify / bringup-plan

Rule: flow_compliance_check.py --phase 2 --strict-structural Overall: PASS is required for Phase 2 to be considered complete. PASS_WITH_WAIVERS requires a corresponding waivers.json entry tagged review_required: true.


Read the full file on GitHub · 54 lines

Changes

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.

  1. 6d ago Changed · +11 lines af45a4e925ab
  2. 9d ago First seen · 43 lines · 55 tokens per session scan A 6a255b687908

Subscribe to this mod's changes

vibe-ic-phase2 is a command published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 1,086 once invoked, about $0.0003 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.