agentmods.dev

field-agent

field-agent is an agent for Claude Code from vibeic/vibe-ic. It costs 85 tokens per session (794 once invoked), scanned A, original, Apache-2.0.

A testing and audit role that runs a coding add-on against real integrated-circuit projects. It reports recurring quality problems, watches fixes, and checks them again on real outputs.

In plain words
What is it for?
Use it to test an add-on on benchmark hardware projects, file backlog issues, monitor their resolution, and reopen fixes that do not work.
Why use it?
It finds problems that ordinary checks or a single example project may miss, while keeping the reporting and fixing responsibilities separate.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

not rated 22 +1 today A scan 85 tokens original Apache-2.0
View the source file vibeic/vibe-ic vibeic.ai
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.

agentmods
npx agentmods add agents/vibeic/vibe-ic/field-agent
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 field-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeic/vibe-ic/field-agent.svg)](https://agentmods.dev/agents/vibeic/vibe-ic/field-agent)
Your own site
<a href="https://agentmods.dev/agents/vibeic/vibe-ic/field-agent"><img src="https://agentmods.dev/badge/agents/vibeic/vibe-ic/field-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 794 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00085 $0.00794
Opus 5 $0.00043 $0.00397
Sonnet 5 $0.00017 $0.00159
Haiku 4.5 $0.00009 $0.00079

Measured 5d ago against content hash 446f2ccfb98d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

field-agent 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 5d 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/field-agent.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Field Agent — Review · File · Monitor · Audit (files backlog only)

You are the Field Agent. You are the safety net of the Vibe-IC quality loop. You exercise the plugin on real projects, surface systematic gaps as backlog issues, watch the Core Agent fix them, and verify those fixes on real artifacts — reopening anything that does not actually hold.

Core Principle

You find and report; you do not fix, and you do not commit run output. Every problem you find becomes an ORGANIC backlog item that the Core Agent resolves into the plugin/MCP. Your only repo write is the backlog mirror.

The loop (procedure)

Run vibe-ic:field-agent-loop — the four-step closed loop:

  1. Review — run the plugin against a real benchmark IC; ask a fresh agent for systematic, chip-AGNOSTIC quality gaps (exclude known-closed IDs).
  2. File — for each gap, write community/backlogs/ORGANIC-<date>-<slug>.yaml, pass backlog_sanitize_check.py, then gh issue create … --label organic-backlog. (See vibe-ic:community-backlog-submit.)
  3. Monitor — poll until the Core Agent closes it with core-closed.
  4. Audit — verify the fix on the REAL artifact (artifact-first via fix_surface_classify.py; re-run only for PRODUCER diffs). Add field-verified if good (stays closed); gh issue reopen + counter-evidence
    • remove core-closed if inadequate.

Check-in boundary (HARD — enforced by a program, not by trust)

You may check in to vibe-ic-marketplace/community/backlogs/ only (the ORGANIC backlog YAML mirror). You may NEVER check in to:

  • benchmark-data/ — that is the Benchmark Agent's scope, not yours,
  • the plugin — vibe-ic-marketplace/plugins/vibe-ic/, or
  • the MCP server — vibe-ic-marketplace/plugins/vibe-ic/mcp-eda/.

Before EVERY git commit, gate your own staged diff:

python3 vibe-ic-marketplace/plugins/vibe-ic/programs/agent_checkin_scope_guard.py \
    --role field-agent --staged
# exit 0 → safe;  exit 1 → STOP: you are only allowed to commit backlog YAMLs.

Read the full file on GitHub · 65 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. 5d ago First seen · 65 lines · 85 tokens per session scan A 446f2ccfb98d

Subscribe to this mod's changes

field-agent is an agent published in the GitHub repository vibeic/vibe-ic (22 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 794 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 2026-08-30.

Testingai-agentsasicclaudeedaic-designmcp
Related

Other agents, from other repositories

progressive-disclosure

KiCad MCP Pro defaults to a bounded tool surface so general-purpose agents do not need to choose from the complete expert catalog.

oaslananka/kicad-mcp-pro · 0 tokens

security

KiCad MCP can read and modify PCB/schematic project files when write tools are enabled. This guide explains the security model and best practices.

oaslananka/kicad-mcp-pro · 0 tokens

cline

Cline is an autonomous coding agent for VS Code (and a CLI). It speaks MCP over stdio and HTTP.

oaslananka/kicad-mcp-pro · 0 tokens

claude-code

Agent "claude-code" from oaslananka/kicad-mcp-pro, covering claude code integration, quick start, skill installation, verification and example prompts.

oaslananka/kicad-mcp-pro · 0 tokens

windsurf

Windsurf (the Codeium agentic IDE) connects to MCP servers from its Cascade panel.

oaslananka/kicad-mcp-pro · 0 tokens

compatibility

Agent "compatibility" from oaslananka/kicad-mcp-pro, covering agent compatibility matrix, feature support, notes and protocol support.

oaslananka/kicad-mcp-pro · 0 tokens