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-review-gategit 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-review-gate)<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/gateway-review-gate"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/gateway-review-gate/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-review-gate"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/gateway-review-gate.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 | $0.00030 | $0.00629 |
| Opus 5 | $0.00015 | $0.00315 |
| Sonnet 5 | $0.00006 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
gateway-review-gate 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gateway Review Gate
Use this skill during Gateway review, verify, and audit stages when a task has implementation artifacts, a qualitySpec, acceptance criteria, or a definition of done.
Contract
Review and verification measure the work against the implementation spec, not against a software-only checklist.
Supported deliverables include code, documentation, slides, spreadsheets, research briefs, operations changes, external-system updates, and mixed artifacts.
Review Mode
- Identify the artifact type and intended outcome.
- Read the task description,
qualitySpec, acceptance criteria, constraints, required artifacts, required evidence, and definition of done. - Inspect the produced artifacts and prior stage evidence.
- For code changes, apply autoreview-style scrutiny for correctness bugs, regressions, security issues, and missing tests.
- For non-code artifacts, check completeness, factual support, audience fit, formatting constraints, required links/files, and stated delivery requirements.
- Return
failwith actionable feedback if material issues remain. - Return
blockedwithneeds_user_inputorneeds_credentialswhen the spec, approval, credential, or external dependency is missing.
Verify Mode
- Use the smallest sufficient proof for the artifact type.
- Run declared verification commands when applicable.
- Inspect required files, links, screenshots, logs, or external records when commands are not the right proof.
- Cite every acceptance criterion and definition-of-done item in artifacts, evidence, or decisions.
- Return
passonly when the evidence proves completion. - If proof fails because implementation is wrong, return
failwithfailureClass: "implementation_failed". - If proof cannot run or evidence is unavailable, return
blockedorfailwith the specific next action.
OpenCode Requests
Use OpenCode-native questions and permission requests when you need human input or approval. Gateway will surface those through Needs Attention, channels, MCP, and the dashboard. Do not create a separate request store.
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.
- 12d ago First seen · 52 lines · 30 tokens per session scan A 33ab61671982
gateway-review-gate is a skill published in the GitHub repository joe-broadhead/open-cowork (11 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 629 once invoked, about $0.0002 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
code-reviewer
Becomes a senior code reviewer who evaluates pull requests and code changes for correctness, security, performance, and maintainability. Use when the user asks for code review, PR feedback, code quality assessment, or merge readiness evaluation. Do NOT use when writing new code, debugging runtime errors, designing…
Review a GitHub PR (via gh)
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Design doc (write -> review loop)
Draft a design document and iterate writer/reviewer subagents until consensus.
Implement (multi-agent loop)
Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.
Review changes (multi-agent)
Delegate read-only reviewers over the local changes/branch and consolidate findings.
Refactor (behavior-preserving)
Improve code structure in small, safe steps without changing behavior.