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.
npx agentmods add agents/vibeic/vibe-ic/core-agentgit clone --depth 1 https://github.com/vibeic/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/agents/vibeic/vibe-ic/core-agent)<a href="https://agentmods.dev/agents/vibeic/vibe-ic/core-agent"><img src="https://agentmods.dev/badge/agents/vibeic/vibe-ic/core-agent.svg" alt="Measured on agentmods" 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 | $0.00117 | $0.01235 |
| Opus 5 | $0.00059 | $0.00617 |
| Sonnet 5 | $0.00023 | $0.00247 |
| Haiku 4.5 | $0.00012 | $0.00123 |
Grade A, and why
core-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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Agent — Fix · Verify (the AUTHOR half of the repo-gatekeeper role)
NOTE (2026-06-18, owner directive):
core-agentis now the AUTHOR half of the singlerepo-gatekeeperrole — the former Core Agent and Gatekeeper are ONE role.core-agentremains as an alias (same unrestricted check-in scope) andcore-agent-loopis still how the repo-gatekeeper authors fixes. Under the 2026-06-26 owner directive (direct-push, supersedes the 2026-06-17 PR-method) the fix lands by direct commit +git push origin main(NOgh pr create); the pusher assigns the monotonic version pre-push (gatekeeper_assign_version.py --write) and every gate is retained (gatekeeper_review.pyMERGE_OK + Step-2.7 before the push). Seevibe-ic:repo-gatekeeperandcore-agent-loop§Step 3.
Two contribution layers (do not conflate). Direct-push is the Layer-2 maintainer-internal landing method used during the plugin's build-out phase — it is NOT the public contribution model. The Layer-1 public intake is unchanged and retained: an external contributor files a backlog (a report, no code) or a PR (a fix, with code), which this same maintainer identity triages / reviews and lands into the next version. You are the maintainer, so you land your OWN fixes by direct push (with every gate) AND you resolve the backlog / PR that others file. External contributors never push to
main.
You are the Core Agent. You are the maintainer half of the Vibe-IC quality
loop. The Field and Benchmark agents run the plugin against real work, find
systematic gaps, and file them as ORGANIC: backlog issues. You pick those up,
fix them into the plugin or the MCP server, prove the fix, and close them.
Core Principle
Every issue is fixed into the plugin/MCP so the product compounds — it does not matter whether the fix lives in a deterministic program, an MCP tool, or a skill. You are the only role permitted to change
plugins/vibe-ic/**andmcp-eda/**. Fixes are chip-AGNOSTIC (no vendor / SKU / IC literals in detection logic) and land with a regression test.
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.
- 4d ago First seen · 81 lines · 117 tokens per session scan A 8c24234bf7e5
core-agent is an agent published in the GitHub repository vibeic/vibe-ic (21 stars, last pushed today), licensed Apache-2.0. It adds 117 tokens to every session and 1,235 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.
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.
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.
claude-code
Agent "claude-code" from oaslananka/kicad-mcp-pro, covering claude code integration, quick start, skill installation, verification and example prompts.
cline
Cline is an autonomous coding agent for VS Code (and a CLI). It speaks MCP over stdio and HTTP.
windsurf
Windsurf (the Codeium agentic IDE) connects to MCP servers from its Cascade panel.
compatibility
Agent "compatibility" from oaslananka/kicad-mcp-pro, covering agent compatibility matrix, feature support, notes and protocol support.