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-improvegit 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-improve)<a href="https://agentmods.dev/skills/mhawthorne/gza/gza-plan-improve"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-plan-improve/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-improve"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-plan-improve.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 | $0.00027 | $0.01248 |
| Opus 5 | $0.00014 | $0.00624 |
| Sonnet 5 | $0.00005 | $0.00250 |
| Haiku 4.5 | $0.00003 | $0.00125 |
Grade A, and why
gza-plan-improve 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 10d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gza Plan Improve
Refine a draft plan through a deliberate question loop. Use this when the user has a rough plan, an incomplete completed plan task, or a draft that needs sharper scope, acceptance criteria, sequencing, risks, and test strategy before implementation begins.
Inputs
Accept one of these inputs:
- Preferred: a full prefixed plan task ID (for example,
gza-1234) - Also supported: pasted draft plan text
- Optional: extra constraints, related task IDs, or notes about what feels weak
If the user provides neither a full prefixed plan task ID nor draft plan text, ask for the current draft or plan task first.
Use the full prefixed task ID for all gza commands.
Goal
Produce an improved plan, not just a score.
The skill should:
- identify the highest-leverage gaps in the current draft
- ask concise questions to close those gaps
- confirm assumptions explicitly instead of guessing
- rewrite the plan into a cleaner, more implementation-ready shape
- call out any remaining blockers or open questions
This is different from /gza-plan-review:
/gza-plan-reviewdecidesGo/No-go/gza-plan-improveactively helps the user strengthen the plan first
Process
Step 1: Gather the current plan and context
If the input is a full prefixed plan task ID, inspect it with:
uv run gza show <TASK_ID>
uv run gza log <TASK_ID>
Use that output to extract:
- task type and status
- original prompt
- current plan/report content
- nearby context from logs that explains uncertainty, blockers, or assumptions
If the task is not found or is not a plan task, stop and explain the mismatch.
If the input is draft text instead of a task ID, use the provided draft as the working plan.
Step 2: Diagnose the weakest parts first
Evaluate the draft against these plan dimensions:
- Problem framing
- Is the user problem or objective specific?
- Does the draft explain why the work matters?
- Scope and boundaries
- What is explicitly in scope?
- What is explicitly out of scope?
- Which files, modules, systems, or surfaces are likely affected?
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.
- 10d ago First seen · 179 lines · 27 tokens per session scan A 390f5ee3778e
gza-plan-improve is a skill published in the GitHub repository mhawthorne/gza (12 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,248 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.