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-behavior-checkgit 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-behavior-check)<a href="https://agentmods.dev/skills/mhawthorne/gza/gza-behavior-check"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-behavior-check/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-behavior-check"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-behavior-check.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 | $0.00059 | $0.03383 |
| Opus 5 | $0.00030 | $0.01691 |
| Sonnet 5 | $0.00012 | $0.00677 |
| Haiku 4.5 | $0.00006 | $0.00338 |
Grade A, and why
gza-behavior-check 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavior conformance check
Check gza's implementation against the behavior specs in specs/behavior/ and
report every place the code diverges from the intended behavior.
The one thing that makes this skill different
This is the inverse of gza-spec-review-all:
gza-spec-review-all |
gza-behavior-check (this skill) |
|
|---|---|---|
| Source of truth | the code | the behavior spec |
| A mismatch means | the doc drifted → flag the doc | a finding: a code bug or a spec gap |
| Reviews | specs/features/ (proposals) |
specs/behavior/ (requirements) |
Critical: the behavior spec is the contract. When code and spec disagree, that is a finding to surface, not license to "fix" the spec to match the code. You MUST NOT edit the code or the spec in this skill. You produce a report; a human (or a follow-up task) decides which side is wrong.
When to use
- "Does the code conform to the behavior spec?" / "check behavior conformance"
- After changing the engine, recovery, rebase, or merge logic
- Before ratifying a draft behavior spec as agreed contract
- When investigating a lifecycle bug, to see if it's a known divergence
Inputs (optional scope)
- No argument — check every doc in
specs/behavior/. - A doc name (e.g.
lifecycle-engine.md) — check only that doc. - An assertion-ID prefix (e.g.
LE-§6) — check only assertions under that section.
Process
Step 1 — Build the assertion list
Read every in-scope doc under specs/behavior/. Extract each normative statement into
an atomic, checkable assertion. Normative statements are:
- RFC-2119 keywords: MUST / MUST NOT / SHOULD / SHOULD NOT / MAY.
- The numbered invariants (overview) and principles (
P*, for exampleP1–P6). - Each ordered rule (
§1–§8) — guard → action pairs. - The parked reason codes table (the closed set).
- The policy knobs table (what is contract: the existence of the bound/gate; the value is not).
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 · 282 lines · 59 tokens per session scan A 356c44b3867a
gza-behavior-check is a skill published in the GitHub repository mhawthorne/gza (12 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 3,383 once invoked, about $0.0003 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
trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens.
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
agent-builder
Load before calling build-agent for a new or existing n8n Agent. Governs prerequisite creation, faithful handoff of the user's request, agent targeting across turns, builder questions, testing, and publishing. Use directly for routine follow-ups when the conversation already targets an Agent; rerun intent-recognition…
ccg-workflow
How to run a non-trivial change end to end with the CCG role tools (ccganalyze / ccgdesign / ccgbuild / ccgdebug / ccgoptimize / ccgreview / ccgtest) and the verify- quality gates. Use when a task is a whole feature, a refactor, a bug whose cause is not yet known, or any change large enough that one straight-through…
config-evals
Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it…
writing-tests
Write unit tests, component tests, and integration tests for AiderDesk using Vitest and React Testing Library. Use when creating new tests, adding test coverage, configuring mocks, setting up test files, or debugging failing tests.