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 agentmods add skills/tommymorgan/claude-plugins/cli-testing-patternsnpx skills add tommymorgan/claude-plugins --skill cli-testing-patternsgit clone --depth 1 https://github.com/tommymorgan/claude-pluginsWhat 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 | $0.00053 | $0.01982 |
| Opus 5 | $0.00026 | $0.00991 |
| Sonnet 5 | $0.00011 | $0.00396 |
| Haiku 4.5 | $0.00005 | $0.00198 |
Grade C, and why
CLI Testing Patterns scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$TMPDIR" How it starts
The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Testing Patterns
Purpose
Provide systematic patterns for autonomous command-line tool exploratory testing. Guide agents through comprehensive CLI testing including help discovery, option validation, error handling checks, exit code verification, and output correctness testing.
Core Testing Methodology
Systematic CLI Testing Approach
Test command-line tools using a structured approach:
- Discovery: Find command and understand its options
- Basic smoke test: Verify command runs
- Help validation: Check help text completeness
- Option testing: Test all flags and arguments
- Error handling: Test edge cases and invalid inputs
- Output validation: Verify correctness and formatting
- Scoped comprehensive testing: Focus on changed areas
CLI Discovery Methods
Identify command to test from context:
Script path: ./scripts/build.sh
Binary name: mycommand
Package.json script: npm run test
System command: git status
Verify command exists:
which mycommand
command -v mycommand
[ -f ./script.sh ] && echo "exists"
Help Text Discovery
Common Help Patterns
Try these flags to discover usage:
command --help
command -h
command help
command
Parse Help Output
Extract from help text:
- Available options/flags
- Required vs optional arguments
- Expected input formats
- Subcommands (if applicable)
- Usage examples
Example help parsing:
Usage: deploy [options] <environment>
Options:
-v, --verbose Enable verbose output
-d, --dry-run Show what would be deployed
--config <file> Use custom config
Identifies:
- Required: <environment>
- Optional flags: -v, -d, --config
- Config file option
Smoke Testing
Basic Execution Tests
Test command works at all:
# Version check
command --version
command -v
# No arguments (if allowed)
command
# Help (should never error)
command --help
Verify:
- Command executes without crashing
- Returns appropriate exit code
- Produces expected output or error
What ships with it
2 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.
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.
- yesterday First seen · 383 lines · 53 tokens per session scan C 7ef7b95f3b46
CLI Testing Patterns is a skill published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,982 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…