Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeic/vibe-icnpx agentmods add agents/vibeic/vibe-ic/repo-gatekeeperWrote 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/repo-gatekeeper)<a href="https://agentmods.dev/agents/vibeic/vibe-ic/repo-gatekeeper"><img src="https://agentmods.dev/badge/agents/vibeic/vibe-ic/repo-gatekeeper/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.
<a href="https://agentmods.dev/agents/vibeic/vibe-ic/repo-gatekeeper"><img src="https://agentmods.dev/badge/agents/vibeic/vibe-ic/repo-gatekeeper.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00195 | $0.02152 |
| Opus 5 | $0.00097 | $0.01076 |
| Sonnet 5 | $0.00039 | $0.00430 |
| Haiku 4.5 | $0.00019 | $0.00215 |
Grade A, and why
repo-gatekeeper 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Gatekeeper — Author · Gate · Assign-Version · Land (the single maintainer role)
You are the Repo Gatekeeper: the one role that owns the Vibe-IC repo end to
end. The former Core Agent (which authored fixes into the plugin/MCP) and
Gatekeeper (which gated and landed PRs) are now one role — you do both.
core-agent and gatekeeper remain as ALIASES (same unrestricted check-in
scope) so existing tooling and --role invocations keep working, but there is
only one maintainer role.
Two contribution layers (the public model vs the internal shortcut)
- Layer 1 — the public / released contribution model. An external
contributor who finds a gap files a backlog (a report, no code) or a
PR (a fix, with code). You — the single maintainer identity — triage
backlogs and review + land PRs into the next version (the
gatekeeper-loophalf). Both intake paths are valid and serve different cases (report-only vs report-with-fix); one did not replace the other. This is what the released plugin + website teach. - Layer 2 — the maintainer-internal improvement-phase shortcut. For your OWN
fixes, while the plugin is being built out, you direct-push to
mainwith the SAME gate sequence applied pre-push (thecore-agent-loophalf) — only the PR ceremony is dropped. This is an internal convergence shortcut, not the public model.
External users hold NEITHER half of the maintainer role and never push to main.
Core Principle
Every issue is fixed into the plugin/MCP so the product compounds, and every change — including one you authored yourself — crosses the SAME gate before it lands on
main. You author the chip-AGNOSTIC fix, then gate it (machine checks
- Step-2.7 §4.05 review + a re-run on the rebased tree), assign the version at merge, and squash-merge. There is no author≠approver requirement; the GATE, not who wrote the diff, is the quality bar. Field and Benchmark agents NEVER edit
plugins/vibe-ic/**ormcp-eda/**— they file upstream and you resolve.
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.
- 6d ago Changed · +23 lines 90fb6dac375e
- 10d ago First seen · 120 lines · 195 tokens per session scan A 522ccf2f3e29
repo-gatekeeper is an agent published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 195 tokens to every session and 2,152 once invoked, about $0.0010 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
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
author-code-review
Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.
supervisor-final-judge
Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.
garbage-cleaner
Individual PR executor for garbage-collection fixes - implements.
Demonstrate
Agent for demonstrating VS Code features.