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 pantheon-org/tekhne --skill behavior-validatorgit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/behavior-validator)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/behavior-validator"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/behavior-validator/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/pantheon-org/tekhne/behavior-validator"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/behavior-validator.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 | $0.00113 | $0.01265 |
| Opus 5 | $0.00056 | $0.00633 |
| Sonnet 5 | $0.00023 | $0.00253 |
| Haiku 4.5 | $0.00011 | $0.00127 |
Grade A, and why
cfn-behavior-validator 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 9d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CloudFormation Resource Update Behavior Validator
Purpose
Empirically validate how CloudFormation handles specific resource property changes by deploying a controlled test stack, making a targeted change, and observing actual CFN events — then deciding whether workarounds are justified.
Workflow
1. Research
- Find the resource's CloudFormation reference page; note "Update requires" for the target property.
- Search GitHub (AWS CDK repo), Stack Overflow, and AWS re:Post for community reports of discrepancies.
- State a hypothesis: "Docs say Replacement — does CFN actually replace the resource?"
2. Design Minimal Test Stack
- Use a non-production, disposable environment.
- Isolate the single property under test; remove unrelated resources.
- Define observable success criteria (e.g. DELETE + CREATE events for the resource type).
// Example: minimal CDK stack parameterised via context
export class BehaviorTestStack extends cdk.Stack {
constructor(scope: Construct, id: string, props?: cdk.StackProps) {
super(scope, id, props);
// Add only the resource under test, driven by this.node.tryGetContext(...)
}
}
3. Execute Test
# 1. Deploy initial state
cdk deploy --require-approval never
# 2. Record resource ARNs / IDs, confirm any required manual steps (e.g. email confirmation)
# 3. Make the single property change, then redeploy
cdk deploy --require-approval never
# 4. Inspect CFN events — stop and debug if deployment fails before proceeding
aws cloudformation describe-stack-events \
--stack-name <stack-name> \
--query 'StackEvents[?ResourceType==`<ResourceType>`].[Timestamp,ResourceStatus,ResourceStatusReason]' \
--output table
Validation gates:
- If initial deployment fails → stop and fix before making any changes.
- If events show unexpected behavior → document immediately and abort further changes.
- If behavior is ambiguous → repeat the test to confirm repeatability.
4. Document Findings & Decide
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .audits/2026-02-21/analysis.md 8.2 KB
- .audits/2026-02-21/audit.json 148 B
- .audits/2026-02-21/remediation-plan.md 240 B
- .audits/2026-02-22/analysis.md 8.2 KB
- .audits/2026-02-22/audit.json 148 B
- .audits/2026-02-22/remediation-plan.md 240 B
- .audits/2026-02-23/analysis.md 8.2 KB
- .audits/2026-02-23/audit.json 147 B
- .audits/2026-02-23/remediation-plan.md 236 B
- .audits/2026-03-02/analysis.md 1.1 KB
- .audits/2026-03-02/audit.json 417 B
- .audits/2026-03-02/remediation-plan.md 2.3 KB
- .audits/latest 10 B
- .tessl-plugin/plugin.json 792 B
- CHANGELOG.md 1.0 KB
- evals/scenario-01.md 4.8 KB
- evals/scenario-02.md 3.6 KB
- evals/scenario-03.md 3.9 KB
- evals/scenario-04.md 4.0 KB
- evals/scenario-05.md 3.4 KB
- references/sns-testing-guide.md 7.6 KB
- scripts/compare-resources.sh 3.4 KB runs code
- scripts/watch-cfn-events.sh 2.2 KB runs code
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.
- 9d ago First seen · 118 lines · 113 tokens per session scan A 5cfd5892f51c
cfn-behavior-validator is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 1,265 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
testing-setup
Analyze and create a testing strategy for native Android apps - install testing libraries, set up test infrastructure, create harnesses for unit tests, UI tests, screenshot tests, and end-to-end tests.
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…
cherry-pr-test
Test Cherry Studio PRs by resolving and checking out a PR, statically inspecting its changes, running interactive UI tests against a safely tracked Electron instance through CDP, producing a structured report, cleaning up only the owned test instance, and restoring the original branch.
winui-ui-testing
Automated UI testing for Windows desktop apps — generate a batch test script with the winapp ui UI Automation harness, run all tests in one pass, read results. Covers element assertions, interactions, value checking (TextBox, ComboBox, ToggleSwitch), keyboard shortcuts and typing (send-keys), hover, drag-and-drop…
web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses Playwright to navigate sections, fill forms, read tables and reports, and perform user actions in a browser.