gateway-supervisor

gateway-supervisor is a skill for Claude Code, Codex from joe-broadhead/open-cowork. It costs 23 tokens per session (514 once invoked), scanned A, original, MIT.

A supervisor workflow for managing a durable Gateway roadmap, meaning a long-running plan whose tasks and events are stored for later turns. It checks roadmap state and decides what action, if any, is needed.

In plain words
What is it for?
It is for reviewing Gateway roadmaps, creating needed tasks, requesting clarification or permission, reporting progress, proposing completion, or deliberately taking no action when nothing is needed.
Why use it?
It keeps roadmap progress, task status, events, permissions, and completion decisions in one existing system instead of creating duplicate tracking records.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

Good fit It is for reviewing Gateway roadmaps, creating needed tasks, requesting clarification or permission, reporting progress, proposing completion, or deliberately taking no action when nothing is needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joe-broadhead/open-cowork/gateway-supervisor
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.

Any agent
npx skills add joe-broadhead/open-cowork --skill gateway-supervisor
Clone the repo
git clone --depth 1 https://github.com/joe-broadhead/open-cowork

Made for: Claude Code, Codex.

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 gateway-supervisor

README.md
[![agentmods](https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/gateway-supervisor/github.svg)](https://agentmods.dev/skills/joe-broadhead/open-cowork/gateway-supervisor)
Your own site
<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/gateway-supervisor"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/gateway-supervisor/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.

agentmods 80×15 button for gateway-supervisor

Your own site · 80×15
<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/gateway-supervisor"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/gateway-supervisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 514 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00023 $0.00514
Opus 5 $0.00012 $0.00257
Sonnet 5 $0.00005 $0.00103
Haiku 4.5 $0.00002 $0.00051

Measured 12d ago against content hash 04ddfdbba7c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gateway-supervisor 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 12d 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.

products/gateway/src/templates/skills/gateway-supervisor/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gateway Supervisor

Use this skill when running a roadmap supervisor turn for Gateway.

Contract

Gateway owns roadmap state, tasks, events, bindings, notifications, completion proposals, and supervisor cursors. OpenCode owns the agent session, questions, permissions, tools, skills, model execution, and message history.

Supervise the assigned roadmap only. Do not create a second task list, request store, status database, or project memory outside Gateway.

Behavior

  1. Inspect the roadmap, task state, recent events, active gates, questions, permissions, alerts, and roadmap memory provided in the prompt.
  2. Decide whether the roadmap needs new tasks, clarification, permission, blocking, a progress digest, completion proposal, or no action.
  3. Prefer no action when current tasks already cover the roadmap and no human decision is needed.
  4. Use Gateway MCP tools only for durable changes.
  5. Use OpenCode-native questions and permission requests for human input or approval.
  6. Never mark a roadmap complete without an explicit completion policy and sufficient evidence.
  7. Repeat the exact turn object from the prompt in the final JSON; Gateway rejects stale or mismatched turns.
  8. Treat create_task as a proposal unless the prompt says direct creation is explicitly allowed by policy.

Final JSON

End supervisor turns with a fenced JSON object:

{"turn":{"supervisorId":"supervisor_...","roadmapId":"roadmap_...","leaseOwner":"gateway-...","cursorEventId":0},"status":"ok|blocked|needs_user|completion_proposed|failed","summary":"what changed","actions":[{"type":"create_task|ask_question|request_permission|block_roadmap|propose_completion|schedule_next_review|summary|none","summary":"operator-readable action"}],"questions":["questions for the user"],"proposedTasks":[{"title":"task title","description":"task description","priority":"HIGH|MEDIUM|LOW"}],"completion":{"recommendation":"not_done|ready_for_user_approval|done","evidence":["evidence refs"],"risks":["residual risks"]},"nextReviewAt":"ISO timestamp"}

Read the full file on GitHub · 41 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. 12d ago First seen · 41 lines · 23 tokens per session scan A 04ddfdbba7c9

Subscribe to this mod's changes

gateway-supervisor is a skill published in the GitHub repository joe-broadhead/open-cowork (11 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 514 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

feishu-calendar

A Feishu calendar and scheduling skill. It manages calendars and events and can check when people are available or busy.

op7418/CodePilot · 33 tokens

feishu-task

A Feishu task-management skill. Feishu, also called Lark, is a work app with tasks and task lists.

op7418/CodePilot · 115 tokens

automation-architect

Workflow automation design using Zapier, Make, and n8n covering trigger-action architecture, multi-step automation workflows, error handling strategies, personal versus business automation patterns, ROI calculation, and a library of common automation recipes. Use when the user asks about automation architect, related…

FerroxLabs/wayland · 90 tokens

project-manager

Becomes a senior project manager who creates status reports, tracks dependencies, manages risks, and maintains project schedules. Use when the user asks for project status tracking, milestone planning, resource allocation, risk management, or work breakdown structures. Do NOT use when the user needs product…

FerroxLabs/wayland · 87 tokens

customer-support-specialist

Becomes a seasoned customer support specialist who triages issues, crafts empathetic responses, manages escalation workflows, and builds knowledge base articles for recurring problems. Use when the user needs help writing customer responses, classifying support tickets, designing escalation procedures, or creating FAQ…

FerroxLabs/wayland · 96 tokens

hr-specialist

Becomes a senior HR specialist who designs interview frameworks, facilitates performance review cycles, builds compensation analysis models, and creates onboarding programs grounded in best practices. Use when the user needs interview guides, evaluation rubrics, job descriptions, or onboarding checklists. Use for…

FerroxLabs/wayland · 103 tokens