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 latestaiagents/agent-skills --skill skill-testinggit clone --depth 1 https://github.com/latestaiagents/agent-skillsWrote 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/latestaiagents/agent-skills/skill-testing)<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/skill-testing"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/skill-testing.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.01925 |
| Opus 5 | $0.00049 | $0.00962 |
| Sonnet 5 | $0.00020 | $0.00385 |
| Haiku 4.5 | $0.00010 | $0.00193 |
Grade A, and why
skill-testing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Testing
An untested skill is a skill that silently breaks. Build a test harness covering frontmatter, content, and activation, run it in CI, and you'll catch regressions long before users file bugs.
When to Use
- Setting up a new skills repository
- Adding skills to an existing repo without test coverage
- Debugging why a skill exists but never activates
- Reviewing PRs that add or modify skills
Three Layers of Testing
- Static validation — frontmatter parses, required fields present
- Content lint — length, structure, code-block sanity
- Activation testing — does the skill fire on realistic queries?
Layer 1: Static Validation
import matter from "gray-matter";
import { readFileSync } from "fs";
import { globby } from "globby";
async function validateAll() {
const files = await globby("skills/**/SKILL.md");
const errors: string[] = [];
for (const file of files) {
const raw = readFileSync(file, "utf-8");
let parsed;
try {
parsed = matter(raw);
} catch (e) {
errors.push(`${file}: invalid YAML`);
continue;
}
const { data } = parsed;
if (!data.name) errors.push(`${file}: missing name`);
if (!data.description) errors.push(`${file}: missing description`);
if (data.description && data.description.length < 50) {
errors.push(`${file}: description too short (${data.description.length} chars)`);
}
// Name must match directory
const dirName = file.split("/").slice(-2)[0];
if (data.name && data.name !== dirName) {
errors.push(`${file}: name '${data.name}' doesn't match directory '${dirName}'`);
}
}
if (errors.length) {
console.error(errors.join("\n"));
process.exit(1);
}
}
validateAll();
Run on every PR. Catches 80% of authoring mistakes.
Layer 2: Content Lint
Check the body for common quality issues:
function lintBody(body: string, file: string) {
const issues = [];
if (body.length > 15_000) issues.push("body too long (>500 lines equiv)");
if (!body.includes("## When to Use") && !body.includes("## When To Use")) {
issues.push("missing 'When to Use' section");
}
if (!body.includes("## Best Practices")) {
issues.push("missing 'Best Practices' section");
}
if (!/```/.test(body)) issues.push("no code example");
// detect stale model IDs
if (/claude-3[.-]/.test(body)) issues.push("stale model ID (claude-3-*)");
// detect TODO markers
if (/TODO|FIXME|XXX/.test(body)) issues.push("contains TODO marker");
return issues.map((i) => `${file}: ${i}`);
}
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.
- 3d ago First seen · 245 lines · 99 tokens per session scan A 1692aa8b1428
skill-testing is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 1,925 once invoked, about $0.0005 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
agent-implementer-sparc-coder
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder.
agent-tdd-london-swarm
Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
moai-workflow-tdd
Test-Driven Development workflow specialist using RED-GREEN-REFACTOR cycle for test-first software development. Use when developing new features from scratch or when behavior specification drives implementation.
tdd-enforcement
Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.