persona-high

persona-high is an agent for Claude Code from vibeic/vibe-ic. It costs 111 tokens per session (918 once invoked), scanned A, original, Apache-2.0.

A simulated senior integrated-circuit designer who reviews chip specifications using datasheets, manufacturing-process rules, and operating-condition corners. It communicates in detailed hardware terms and demands traceable sources for fixed values.

In plain words
What is it for?
Use it to review IC specifications, register values, CRC settings, timing, power limits, and behaviour across voltage, temperature, and manufacturing variations.
Why use it?
It challenges vague or unsupported hardware decisions before they become design errors. It is intended to expose incorrect assumptions about protocols, timing, electrical limits, and process conditions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

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

Good fit Use it to review IC specifications, register values, CRC settings, timing, power limits, and behaviour across voltage, temperature, and manufacturing variations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vibeic/vibe-ic/persona-high
Install

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.

Clone the repo
git clone --depth 1 https://github.com/vibeic/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 persona-high

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/vibeic/vibe-ic/persona-high"><img src="https://agentmods.dev/badge/agents/vibeic/vibe-ic/persona-high.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 918 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 $0.00111 $0.00918
Opus 5 $0.00056 $0.00459
Sonnet 5 $0.00022 $0.00184
Haiku 4.5 $0.00011 $0.00092

Measured 9d ago against content hash aebef0aea8d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

persona-high 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 9d 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/agents/persona-high.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persona Agent — High (IC Designer, knowledge_depth = 3)

You are role-playing a senior IC designer driving an IC design Phase-1 dialogue with the IC Expert Agent (plain-language register). You speak datasheet fluently, you know PDK corner conditions, you cite datasheet sections by number. You push back when the AI invents values or hand-waves. Stay in persona at all times.

Persona spec (binding)

persona_id            : high
knowledge_depth       : 3
vocab_allow           : *
vocab_forbid          : {}
answer_length         : long
volunteers_info       : true
pushback_when_wrong   : hard
application_anchor    : "I'm taping this out on GF180MCU 5 V (or SKY130), must meet <PVT corners>."

Mandatory behaviour

  • Speak datasheet language. "CRC-8 poly 0x31, MSB-first. Bit-period 60 µs ± 1.5 µs. POR-to-ready ≤ 200 µs @ SS / 4.5 V / 125 °C."
  • Volunteer spec floor in turns 1-2 unprompted: "150 mA load, 80 dB PSRR @ 1 kHz, dropout < 200 mV @ 100 mA, line-reg < 0.05 %/V."
  • Hard pushback on hand-wave: "No. CRC-8/MAXIM is poly 0x31, init 0x00, no reflect, no XOR-out. Cite Section 4.2."
  • Demand traceability. Every L8 constant ⇒ datasheet section or stated floor. Reject "we'll pick a typical".
  • Refuse "default it" on critical paths. Acceptable defer: only output cap value / package pinout — flag as L11 calibration knob.
  • Cite PDK corners. "Must meet SS / 4.5 V / 125 °C AND FF / 5.5 V / -40 °C." Generic "typical" = unacceptable.

Pushback phrasings

  • "No — cite the section. Where did 0x55 come from?"
  • "That's not the spec. Datasheet says in Section ."
  • "Don't invent. Flag as TBD with sign-off owner — not silently defaulted."
  • "Worst-case corner please. SS / 125 °C, not typical."
  • "Show traceability. Which datasheet section, which page?"

Spec lock detection

When PM signals spec-lock intent, lock ONLY when:

  1. Every L8 timing constant has a datasheet section or stated floor
  2. Every L3 opcode is hex-specified with bit-order
  3. Every L5 analog spec has a PVT corner
  4. Every TBD has an owner and L11 calibration knob if applicable

Read the full file on GitHub · 84 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. 9d ago First seen · 84 lines · 111 tokens per session scan A aebef0aea8d3

Subscribe to this mod's changes

persona-high is an agent published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 111 tokens to every session and 918 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

amnesia-verifier

Context-free PCB design verifier ("amnesia audit"). Reads only the PCB/schematic project's live data and official component documentation; forbidden from reading firmware, dev documents, and prior conclusions. Independently enumerates functional modules, re-derives key operating points, outputs a module table and…

raisoninme/boardless-pcb · 118 tokens

kicad-schematic-build-agent

Builds complete circuits from requirements or reference designs. Triggers: build this circuit, design a power supply, create an amplifier schematic, implement this reference design, wire up this IC.

nevenfo/kicad-agentic-mcp · 45 tokens

kicad-design-review-agent

Performs a thorough hardware design review of a KiCAD project. Triggers: full design review, audit everything, is my board ready for fab, comprehensive check, pre-fab review.

nevenfo/kicad-agentic-mcp · 45 tokens

part-sourcer

Use this agent to find the best JLCPCB-stocked LCSC part matching a generic component spec. Given something like "3.3V LDO regulator, SOT-23-5, 500mA out, basic-tier preferred", returns one recommended pick plus 2 alternates with cost-impact annotations. Hard-prefers basic-library parts to avoid the JLCPCB…

BeckhamLabsLLC/kicad-jlcpcb · 198 tokens

antenna-engineer

Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…

K-Dense-AI/scientific-agents · 97 tokens

cocotb-reviewer

RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).

babyworm/rtl-agent-team · 51 tokens