gateway-planner

gateway-planner is a skill for Claude Code, Codex from joe-broadhead/open-cowork. It costs 17 tokens per session (419 once invoked), scanned A, original, MIT.

A planning guide for OpenCode Gateway, a system that stores roadmaps, scheduled tasks, runs, and workflow events in a database.

In plain words
What is it for?
Use it to clarify outcomes, create roadmaps and scheduler tasks, inspect task or run status, and record acceptance criteria and verification evidence.
Why use it?
It helps keep multi-step work and scheduled execution organized in durable records instead of relying on temporary notes.

Skill for Claude CodeCodex

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

Good fit Use it to clarify outcomes, create roadmaps and scheduler tasks, inspect task or run status, and record acceptance criteria and verification evidence.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/gateway-planner"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/gateway-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 419 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.
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 $0.00017 $0.00419
Opus 5 $0.00009 $0.00210
Sonnet 5 $0.00003 $0.00084
Haiku 4.5 $0.00002 $0.00042

Measured 12d ago against content hash d11ea90794fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gateway-planner 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-planner/SKILL.md · 48 lines

What it actually says

Gateway Planner

Use this skill when planning work with OpenCode Gateway.

Operating Model

  • Treat Gateway SQLite roadmaps, tasks, runs, and channel bindings as the durable execution state.
  • Do not edit Gateway database files directly.
  • Use Gateway MCP tools for roadmaps, tasks, runs, and workflow events.

Tools

  • gateway_roadmap_create creates a durable roadmap.
  • gateway_roadmap_list lists roadmaps.
  • gateway_task_create creates concrete scheduler tasks.
  • gateway_task_list lists task state.
  • gateway_task_get inspects one task.
  • gateway_run_list lists recent execution runs.
  • gateway_run_get inspects one run.
  • gateway_work_events lists Gateway-owned workflow events.

Planning Flow

  1. Clarify the outcome, artifact type, acceptance criteria, and definition of done.
  2. Create a roadmap for multi-step work.
  3. Create small tasks with clear titles, descriptions, priorities, and acceptance notes.
  4. Prefer the default pipeline implement -> review -> verify unless the work clearly needs a custom pipeline.
  5. Put background knowledge, decisions, acceptance criteria, definition of done, required artifacts, and verification evidence in task descriptions, notes, or qualitySpec.
  6. Surface user questions only when execution cannot safely continue.

Task Creation Guidance

  • Keep tasks independently reviewable.
  • Include expected artifacts, definition of done, and verification path in qualitySpec when available; use note for lightweight context.
  • Remember tasks may be code, docs, slides, research, operations, or external-system changes. Make the review/verify criteria artifact-specific.
  • Use HIGH only for tasks that should preempt other work.
  • Do not mark work done manually unless the user explicitly asks.
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 · 48 lines · 17 tokens per session scan A d11ea90794fe

Subscribe to this mod's changes

gateway-planner is a skill published in the GitHub repository joe-broadhead/open-cowork (11 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 419 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.