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 mhawthorne/gza --skill gza-plan-reviewgit clone --depth 1 https://github.com/mhawthorne/gzaWrote 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/mhawthorne/gza/gza-plan-review)<a href="https://agentmods.dev/skills/mhawthorne/gza/gza-plan-review"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-plan-review/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/mhawthorne/gza/gza-plan-review"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-plan-review.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 | $0.00024 | $0.01133 |
| Opus 5 | $0.00012 | $0.00566 |
| Sonnet 5 | $0.00005 | $0.00227 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
gza-plan-review 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gza Plan Review
Run an interactive plan quality gate for a specific plan task before implementation starts.
Inputs
- Required: full prefixed plan task ID (for example,
gza-1234)
If the user did not provide a task ID, ask for it before proceeding.
Use the full prefixed task ID for all gza commands.
Process
Step 1: Inspect the task with built-in gza commands
Run these commands with the provided task ID:
uv run gza show <TASK_ID>
uv run gza log <TASK_ID>
uv run gza history --type plan --limit 10
Use this output to verify:
- task exists
- task type is
plan - task status (
completedis required for aGorecommendation) - final plan output and any failure context
- nearby plan/review history for dependencies and precedent
If the task is not found or is not a plan task, stop and return a no-go with corrective actions.
Step 2: Run the interactive quality gate
Use AskUserQuestion to evaluate each gate area. Ask concise, targeted questions and confirm assumptions explicitly.
Gate areas:
- Scope clarity
- Is the problem statement specific?
- Are boundaries and out-of-scope items explicit?
- Are impacted components/files identified?
- Acceptance criteria
- Are there concrete, testable success criteria?
- Are behavior, edge cases, and failure modes covered?
- Is "done" unambiguous for implementation and review?
- Risks
- Are technical/product risks identified and ranked?
- Are mitigation steps or fallback paths defined?
- Are unknowns called out with a way to resolve them?
- Dependencies
- Are task dependencies (other gza tasks, systems, data, approvals) listed?
- Are dependency states known (ready, blocked, unknown)?
- Is sequencing clear enough to avoid rework?
- Test strategy
- Are required test types named (unit/integration/e2e as relevant)?
- Are key scenarios and regressions enumerated?
- Is verification command strategy clear for implementation work?
Step 3: Score and decide
Assign each gate area one status:
Pass- sufficient for implementationNeeds work- gaps exist but are fixableFail- critical blocker
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 · 144 lines · 24 tokens per session scan A 535465bfa4a9
gza-plan-review is a skill published in the GitHub repository mhawthorne/gza (12 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,133 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
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
tencent-docs
A Tencent Docs assistant for creating, reading, editing, organizing, importing, and exporting online documents, spreadsheets, presentations, diagrams, and forms.
wechat-search
Search WeChat Official Account articles using OpenClaw's web search, Tavily API, and web fetch capabilities with compliance-focused design.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.