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-coherencegit 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-coherence)<a href="https://agentmods.dev/skills/mhawthorne/gza/gza-spec-coherence"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-spec-coherence/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-coherence"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-spec-coherence.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 | $0.00028 | $0.02469 |
| Opus 5 | $0.00014 | $0.01234 |
| Sonnet 5 | $0.00006 | $0.00494 |
| Haiku 4.5 | $0.00003 | $0.00247 |
Grade A, and why
gza-spec-coherence 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavior spec coherence check
Review the behavior spec set itself in specs/behavior/ for authoring quality:
coherence, ownership boundaries, atomic normative text, and plain-language discipline.
This skill is blind to authorship. The behavior spec is a shared artifact that both humans and agents edit, so you judge the text only: never who wrote it.
The one thing that makes this skill different
This is neither an implementation conformance check nor a feature-spec freshness review:
gza-spec-review-all |
gza-behavior-check |
gza-spec-coherence (this skill) |
|
|---|---|---|---|
| Source of truth | the code | the behavior spec | the behavior-spec set as a set |
| A mismatch means | the doc drifted | code diverged or spec is wrong | ownership, wording, or cross-reference discipline drifted |
| Reviews | specs/features/ |
specs/behavior/ vs code |
specs/behavior/ vs itself |
Critical: this skill MUST NOT edit the spec or the code. It reports findings only. Each finding cites file + section and says concretely what to change.
When to use
- "Check the behavior specs for coherence"
- Before ratifying a behavior-spec refactor
- After moving vocabulary or invariants between behavior-spec files
- When a spec change feels repetitive, contradictory, or over-written
- As an author-side gate on edits under
specs/behavior/**
Inputs (optional scope)
- No argument — review the full
specs/behavior/set. - One or more changed files under
specs/behavior/**— review those files against the rest of the set. - A directory/pattern under
specs/behavior/— review matching files, but still load the owning files needed to judge overlap and references.
If the caller provides a change list, do not limit yourself to those files alone: coherence findings often live at the boundary between the changed file and its owner. Primary findings should still be about the changed behavior-spec files unless an owning file must change to resolve a duplicate-ownership problem.
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 · 239 lines · 28 tokens per session scan A 58a10fdae8a9
gza-spec-coherence is a skill published in the GitHub repository mhawthorne/gza (12 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 2,469 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.