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-spec-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-spec-review)<a href="https://agentmods.dev/skills/mhawthorne/gza/gza-spec-review"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-spec-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-spec-review"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-spec-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 | $0.01171 |
| Opus 5 | $0.00012 | $0.00585 |
| Sonnet 5 | $0.00005 | $0.00234 |
| Haiku 4.5 | $0.00002 | $0.00117 |
Grade A, and why
gza-spec-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 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gza Spec Review
Run an interactive quality gate for a specific spec file before implementation starts.
Inputs
- Required: path to a feature spec file (e.g.
specs/features/foo.md)
If the user did not provide a spec path, ask for it before proceeding.
Normalize spec paths:
- If input is just a filename like
foo.md, expand tospecs/features/foo.md - If the file does not exist, stop and report the error
Process
Step 1: Read and understand the spec
Read the spec file in full. Identify:
- The core problem/feature being described
- Concrete claims: file paths, command names, config fields, function signatures, workflow steps
- Acceptance criteria (explicit or implied)
- Dependencies on other specs, tasks, or systems
Step 2: Verify claims against the codebase
For each concrete claim in the spec:
-
File paths - Does the spec reference files that exist?
- Search with Glob for referenced paths
- Flag paths that don't exist and aren't plausible future additions
-
Command/option names - Does the spec describe CLI commands or flags?
- Compare against
uv run gza --helpanduv run gza <command> --help - Flag commands that were renamed or flags that changed
- Compare against
-
Config fields - Does the spec reference configuration options?
- Search
src/gza/config.pyfor referenced field names - Flag fields that were renamed or removed
- Search
-
Code patterns - Does the spec describe specific functions, classes, or modules?
- Search with Grep for referenced identifiers
- Flag identifiers that no longer exist
-
Workflow steps - Does the spec describe a multi-step process?
- Verify each step is still how the feature works
- Flag steps that have been simplified, reordered, or changed
Use git blame/log for context when unsure if something is aspirational vs outdated:
- Recent specs are more likely aspirational
- Old specs with recent code changes around the feature are more likely outdated
Step 3: Run the interactive quality gate
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 · 147 lines · 24 tokens per session scan A 76911e6ce122
gza-spec-review is a skill published in the GitHub repository mhawthorne/gza (12 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,171 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.