Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wardawgmalvicious/agent-confignpx agentmods add skills/wardawgmalvicious/agent-config/test-skillWrote 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/wardawgmalvicious/agent-config/test-skill)<a href="https://agentmods.dev/skills/wardawgmalvicious/agent-config/test-skill"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/test-skill/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/wardawgmalvicious/agent-config/test-skill"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/test-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00179 | $0.03956 |
| Opus 5 | $0.00089 | $0.01978 |
| Sonnet 5 | $0.00036 | $0.00791 |
| Haiku 4.5 | $0.00018 | $0.00396 |
Grade B, and why
test-skill scanned grade B with 1 finding 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 today.
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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills | Select-String '^(fabric|pbir|pbid)-' # must return nothing How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test a skill
Take a drafted skill and end at a validated one: its activation contract written and passing, its behaviour checked in a cold session, and the fixtures it ran against provably unmodified.
This is the second half of /author-skill, which stops at a linted
draft and writes no fixtures on purpose. The coupling between them is
the brief on disk, not session state — so this skill runs cold, in a
fresh session, exactly like /drift-update.
It also runs on a skill that shipped long ago and has since been edited. That case has no brief and needs none; step 1 says where its inputs come from instead.
Repo-relative paths are relative to the agent-config repo
(C:\Repos\Personal\agent-config), not the session's cwd.
What this validates, and what it does not
Skills only — the same scope as author-skill. Rules get exercised
incidentally, because the activation harness checks claude/rules/*.md
alongside skills on the same fixtures, but authoring rule fixtures is
not this skill's job.
Out of scope, with their procedures elsewhere:
| Artifact | Procedure lives in |
|---|---|
| Subagents | tests/agents/security-reviewer/README.md |
| Enforcement hooks | same, plus the direct unit-test pattern in root CLAUDE.md |
| Rules, as authored artifacts | root CLAUDE.md, "Validating a change" |
Phase A — the activation contract
Skip this phase entirely if the skill has no paths: glob. An
unconditional skill has no activation contract, so there is nothing to
fixture and nothing to assert. Say so and go to Phase B; do not
manufacture a fixture to make the phase look done.
1. Read the trigger contract from disk
Two entry paths, and they take their inputs from different files. Establish which one you are on before reading anything.
A newly drafted skill, arriving from /author-skill:
docs/handoffs/execute/<skill-name>.md
Take from it the paths: glob, the named trigger queries, and the
scope decisions. Read it from the file even if you wrote it an hour
ago — the point of the disk contract is that a fresh session with no
memory of the authoring run behaves identically.
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.
- today Changed 7b09a0de2e12
- 2d ago Changed ba2141930ea7
- 7d ago Changed · +40 lines · -56 tokens per session d5487985e6b4
- 8d ago First seen · 299 lines · 235 tokens per session scan B d9bec66e2487
test-skill is a skill published in the GitHub repository wardawgmalvicious/agent-config (1 stars, last pushed yesterday), licensed MIT. It adds 179 tokens to every session and 3,956 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
terraform-test
WORKFLOW SKILL — Write and run Terraform tests (.tftest.hcl). WHEN: "create terraform test", "write tftest", ".tftest.hcl", "mock provider", "test module", "test assertion". USE FOR: test files, run blocks, assertions, mock providers, plan-mode unit tests, apply-mode integration tests, test troubleshooting. DO NOT USE…
ak-test
Set up testing and debug common issues in Agent Kernel projects. This skill guides you through configuring the built-in test framework, writing agent tests, choosing test modes (score, llm, fallback), and troubleshooting common errors.
thousandeyes
ThousandEyes network intelligence integration for monitoring tests, alerts, agents, Internet Insights outages, dashboards, and BGP routes during RCA investigations.
702-technologies-wiremock
Use when you need framework-agnostic WireMock guidance — stub design, JSON or programmatic mappings, precise request matching, response bodies and faults, classpath fixtures, isolation and reset between tests, verification of calls, dynamic ports and base URLs, and avoiding flaky stubs — without choosing Spring Boot…
131-java-testing-unit-testing
Use when you need to review, improve, or write Java unit tests — including migrating from JUnit 4 to JUnit 5, adopting AssertJ for fluent assertions, structuring tests with Given-When-Then, ensuring test independence, applying parameterized tests, mocking dependencies with Mockito, verifying boundary conditions…
132-java-testing-integration-testing
Use when you need to set up, review, or improve Java integration tests — including generating a BaseIntegrationTest.java with WireMock for HTTP stubs, detecting HTTP client infrastructure from import signals, injecting service coordinates dynamically via System.setProperty(), creating WireMock JSON mapping files with…