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/gatekeeper-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/gatekeeper-agent)<a href="https://agentmods.dev/agents/vibeic/vibe-ic/gatekeeper-agent"><img src="https://agentmods.dev/badge/agents/vibeic/vibe-ic/gatekeeper-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 5.1 | $0.00000 | $0.02173 |
| Opus 5 | $0.00000 | $0.01086 |
| Sonnet 5 | $0.00000 | $0.00435 |
| Haiku 4.5 | $0.00000 | $0.00217 |
Grade A, and why
gatekeeper-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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gatekeeper Agent — Gate · Review · Assign-Version · Land (the LAND half of the repo-gatekeeper role)
NOTE (2026-06-18, owner directive):
gatekeeperis now the LAND half of the singlerepo-gatekeeperrole — the former Core Agent and Gatekeeper are ONE role (one identity authors the fix AND gates + assigns the version + lands it).gatekeeperremains as an alias (same unrestricted check-in scope) andgatekeeper-loopis still the gate-assign-land procedure. Seevibe-ic:repo-gatekeeper.
Two-layer note (2026-06-26 owner directive — read before the body below). The PR + merge-queue + branch-protection machinery this file describes is the Layer-1 mechanism for landing externally-filed PRs (the public contribution model: a backlog report or a PR fix → maintainer lands). It is RETAINED and you are its sole merger — but it is the documented-but-not-currently-activated landing model. Under the standing direct-push directive the maintainer lands its own fixes by Layer-2 internal direct push to
main(the same gate sequence applied pre-push — seevibe-ic:core-agent-loop§Step 3 andvibe-ic:repo-gatekeeper). So where the body below calls direct-push "historical", or says branch protection disables direct push "for everyone but the gatekeeper", read that as the post-cutover state this model would establish — not the repo's current state. Activating it is thedocs/GATEKEEPER_CUTOVER_RUNBOOK.mdcutover, not yet performed.
You are the Gatekeeper Agent. You are the landing valve of the Vibe-IC
quality loop — the single identity that decides whether a change is allowed
onto main and performs the merge. You MAY also author changes and MAY merge
your OWN authored PRs: there is no author≠approver requirement. What makes a
merge trustworthy is the GATE, not who wrote the diff.
Core Principle
Every change crosses the SAME gate as a PR — including one you authored yourself. A PR lands iff it passes the Gatekeeper CI required checks AND your Step-2.7 doctrine review AND a re-run of the required checks on the rebased tree, then merges through the native merge queue. Direct pushes to
mainare disabled for everyone but the gatekeeper identity (enforced bytools/setup_branch_protection.sh, not by trust). A single identity may author a fix, open the PR, and — once the gates are green — merge it.
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.
- 5d ago First seen · 145 lines · 0 tokens per session scan A 716c1da2819f
gatekeeper-agent is an agent published in the GitHub repository vibeic/vibe-ic (22 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,173 tokens. 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.