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 skills/jarroslav/agentic-os/gate-arbiternpx skills add Jarroslav/agentic-os --skill gate-arbitergit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/skills/jarroslav/agentic-os/gate-arbiter)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/gate-arbiter"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/gate-arbiter.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 | $0.00164 | $0.03840 |
| Opus 5 | $0.00082 | $0.01920 |
| Sonnet 5 | $0.00033 | $0.00768 |
| Haiku 4.5 | $0.00016 | $0.00384 |
Grade A, and why
gate-arbiter 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gate-arbiter
Single shared resolver for every judgment gate in the SDLC pipeline. Given a gate id and a mode
(hitl or autonomous), it decides how the gate gets settled — human question, deterministic
check, fast-path approval, or dispatched stand-in reviewer — always returns one fixed verdict
shape, and durably records the outcome even when the normal resolution path fails.
This skill decides and logs. It never edits a spec, plan, diff, or evidence file, and it never runs review-lens subagents itself — those live one level down, inside
code-review-orchestrator.
Operating modes
| Mode | Behavior |
|---|---|
hitl |
Every recognized gate goes to AskUserQuestion. No fast-path, deterministic shortcut, or stand-in substitutes for the human's answer. The two code-review gates are the one carve-out: run the inline code-review-orchestrator skill first to produce a report, then ask the human — the report informs the question, it never resolves the gate on its own. |
autonomous |
Resolution tries cheapest-first: deterministic check → pre-classified fast-path → dispatched stand-in subagent. Code-review gates are pinned to the inline skill and never fall through to fast-path or stand-in dispatch. |
An unrecognized gate id is a structural error in either mode, not a judgment call: reject
immediately, decision abort, confidence low, escalation forced.
Gate catalog
gate_id is a frozen, shared-contract enum. Reuse these ids verbatim — never invent new ones,
never abbreviate them.
| Gate ID | Resolver | Kind |
|---|---|---|
requirements.ambiguous |
story-proxy |
subagent |
spec.clarification |
story-proxy |
subagent |
spec.approved |
lead-proxy |
subagent |
plan.approved |
lead-proxy |
subagent |
code-review.final |
code-review-orchestrator |
skill (inline) |
code-review.check |
code-review-orchestrator |
skill (inline) |
qa.drift |
lead-proxy |
subagent |
feature.verification |
lead-proxy |
subagent |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 282 lines · 0 tokens per session scan A 5bc926783d02
gate-arbiter is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 164 tokens to every session and 3,840 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…