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 skills add joe-broadhead/open-cowork --skill gateway-stagegit clone --depth 1 https://github.com/joe-broadhead/open-coworkWrote 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/joe-broadhead/open-cowork/gateway-stage)<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/gateway-stage"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/gateway-stage/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/skills/joe-broadhead/open-cowork/gateway-stage"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/gateway-stage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.00596 |
| Opus 5 | $0.00008 | $0.00298 |
| Sonnet 5 | $0.00003 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
gateway-stage 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 11d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gateway Stage Worker
Use this skill when executing a Gateway scheduler stage in OpenCode.
Contract
Gateway owns scheduling and task state. OpenCode owns the actual agent runtime, tools, MCPs, model execution, questions, permissions, and session history.
Do the assigned stage only. Do not claim the whole task is complete unless this is the final verification stage and the evidence supports it.
Tasks are not always software tasks. They may produce code, docs, slides, research, operations changes, external-system updates, or mixed artifacts. Measure stage success against the task description, qualitySpec, acceptance criteria, constraints, required artifacts, required evidence, and definition of done.
Stage Behavior
implement: make the requested change and provide artifacts/evidence for review.review: compare the work to the implementation spec and definition of done. For code, also identify bugs, risks, missing tests, regressions, and unclear behavior. Fail if material issues remain.verify: run or inspect the smallest sufficient proof for the artifact type. Pass only with sufficient evidence for the spec and definition of done.audit: assess production readiness and broader operational risks.plan: clarify approach, dependencies, and acceptance criteria.
Required Final Output
Finish with a fenced JSON object:
{"status":"pass|fail|blocked","summary":"short result","feedback":"specific feedback for the next attempt if any","failureClass":"blocked|needs_user_input|needs_credentials|flaky_test|unsafe|exceeded_budget|unclear_spec|implementation_failed|verification_failed","artifacts":["short artifact refs"],"evidence":[{"type":"diff|test|command|link|screenshot|log|decision|file|note|other","ref":"file, command, URL, log path, or decision id","summary":"why it matters"}],"decisions":["durable decisions made"]}
Rules
- Use
blockedwhen you need user input, credentials, missing context, or an external dependency. - Use OpenCode-native questions and permission requests for human input or approval; Gateway surfaces them through Needs Attention, channels, MCP, and the dashboard.
- Use
failwhen the stage found fixable issues. - Use
passonly when this stage's requirements are met. - Set
failureClassfor everyfailorblockedresult. - Put actionable retry instructions in
feedback. - List short refs in
artifactsand structured proof inevidence. - If the task has acceptance criteria, definition-of-done items, constraints, required verification commands, required evidence, or required artifacts, cite matching proof before returning
pass.
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.
- 11d ago First seen · 49 lines · 16 tokens per session scan A cbd2d1a48d0e
gateway-stage is a skill published in the GitHub repository joe-broadhead/open-cowork (11 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 596 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.
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.
feishu-task
A Feishu task-management skill. Feishu, also called Lark, is a work app with tasks and task lists.
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…
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…
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…
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…