A test workflow that gives each guard deliberately bad input and checks that the guard rejects it.

Use it to run rejection tests for scripts and to check the staged tree before a release.

It reveals guards that fail to block invalid cases and can stop a release when one has not been tested successfully.

How myICOR/myPKA configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to myICOR/myPKA. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/myICOR/myPKA/main/.claude/skills/red-tests/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/myICOR/myPKA

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/myicor/mypka/red-tests/github.svg)](https://agentmods.dev/skills/myicor/mypka/red-tests)

Your own site

<a href="https://agentmods.dev/skills/myicor/mypka/red-tests"><img src="https://agentmods.dev/badge/skills/myicor/mypka/red-tests/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/myicor/mypka/red-tests"><img src="https://agentmods.dev/badge/skills/myicor/mypka/red-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 503 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00094	$0.00503
Opus 5.5	$0.00038	$0.00201
Sonnet 5.5	$0.00019	$0.00101
Haiku 4.5	$0.00009	$0.00050

Measured 1mo ago against content hash 45eecfd53e11, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

red-tests 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 1mo 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.

.claude/skills/red-tests/SKILL.md · 32 lines

What it actually says

You are Mack. If you are the orchestrator, hand this to the specialist mack; if you are already Mack, act directly.

Run this only when the user asks for it by name.

Read 06 AI Team/AI Team Knowledge/SOPs/SOP-1016-run-the-red-tests-and-gate-a-release.md now and follow it exactly. That file is the procedure; this file is the door.

Run python3 "06 AI Team/AI Team Knowledge/Scripts/run-red-tests.py" with your shell tool, from the folder that holds AGENTS.md, before step 1, unless its output is already below. Read that output; do not run it twice.

!python3 "${CLAUDE_PROJECT_DIR}/06 AI Team/AI Team Knowledge/Scripts/run-red-tests.py"

Script calls the procedure names, by path:

06 AI Team/AI Team Knowledge/Scripts/run-red-tests.py
06 AI Team/AI Team Knowledge/Scripts/release-gate-red-tests.sh
06 AI Team/AI Team Knowledge/Scripts/build-mypka-release.sh
06 AI Team/AI Team Knowledge/Scripts/build-release-zip.sh

Resources (open only when a step names them):

06 AI Team/Agents/Mack/AGENT.md
06 AI Team/AI Team Knowledge/SOPs/SOP-1016-run-the-red-tests-and-gate-a-release.md

Return the completion evidence the procedure's last step names, and nothing it does not.

Changes

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.

1mo ago Changed · +1 lines 45eecfd53e11
1mo ago First seen · 31 lines · 94 tokens per session scan A b50cf23afd64

Subscribe to this mod's changes

red-tests is a skill published in the GitHub repository myICOR/myPKA (318 stars, last pushed 22d ago), licensed MIT. It adds 94 tokens to every session and 503 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-26.

Claude Code Testing ai-team claude-cowork cursor gemini-cli icor

writing-livekit-scenarios

Creates and maintains the scenarios a LiveKit agent simulation runs, and wires the agent to consume them. Use when the user asks "what should I test", "generate simulation scenarios", "write scenarios for my agent", "add a scenario for X", "organize my scenario files", "my simulations are flaky", "the scenario hits my…

fcakyon/claude-codex-settings · 178 tokens

debugging-livekit-agents

Drives a live multi-turn conversation with a LiveKit agent running locally, using lk agent debugger. Use when the user says "test my agent", "try my agent", "does this work", or "why did it call that tool", after editing an agent to check how it behaves, or when an agent on a speech-to-speech model or one that…

fcakyon/claude-codex-settings · 116 tokens

running-livekit-simulations

Runs LiveKit agent simulations and acts on the results. Use when the user says "run my simulations", "regression test my agent before deploying", "run the scenarios", "use lk agent simulate", "did my agent pass", "why did this scenario fail", "run simulations in CI", "test the audio pipeline", "check turn-taking and…

fcakyon/claude-codex-settings · 183 tokens

ui-regression

This skill should be used when the user asks to "verify UI changes", "audit UI quality", "test every screen and action", "run regression QA", "check a deployed UI", or "validate an extension release". Test known web and browser-extension workflows on localhost, staging, or production with action coverage, recovery…

fcakyon/claude-codex-settings · 87 tokens

testing-livekit-agents

Writes turn-level tests for a LiveKit agent in the user's normal test suite: pytest (Python) or Vitest (Node.js). Use when the user asks to "write tests for my agent", "add a test for this tool", "test the handoff", "pin this bug", "why does my agent test fail", or after building or changing agent behavior that needs…

fcakyon/claude-codex-settings · 155 tokens

test-audit

This skill should be used when the user asks to "write a test", "review these tests", "audit tests", "prune low-value tests", or "find duplicate tests", and whenever writing, changing, reviewing, or sweeping tests. Gates new tests and audits low-value, implementation-coupled, or duplicative tests and the test-only…

fcakyon/claude-codex-settings · 79 tokens

myPKA: Skill for Claude Code