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/eveld/claude/follow-test-patternsnpx skills add eveld/claude --skill follow-test-patternsgit clone --depth 1 https://github.com/eveld/claudeWrote 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/eveld/claude/follow-test-patterns)<a href="https://agentmods.dev/skills/eveld/claude/follow-test-patterns"><img src="https://agentmods.dev/badge/skills/eveld/claude/follow-test-patterns.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 | $0.00025 | $0.00753 |
| Opus 5 | $0.00013 | $0.00377 |
| Sonnet 5 | $0.00005 | $0.00151 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
follow-test-patterns 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 6d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Follow Test Patterns
Reference discovered test patterns when writing tests to ensure consistency with project conventions.
When to Use
- Before writing any test file
- When implementing test-related phases in plans
- When user asks you to add tests
Workflow
1. Check for Pattern Document
if [ -f thoughts/notes/testing.md ]; then
# Read and follow patterns
else
# Prompt user to run discover-test-patterns first
echo "No test patterns found. Run discover-test-patterns skill first."
fi
2. Read Pattern Document
Read thoughts/notes/testing.md fully to understand:
- File naming conventions
- Testing framework and imports
- Test structure (table-driven, etc.)
- Assertion style
- Mocking approach
3. Apply Patterns to New Tests
Use the discovered patterns for:
File Naming:
- Follow the pattern (e.g.,
*_test.go,*.test.ts) - Place alongside source or in test directory as per convention
Imports:
- Use same testing framework (testify, jest, pytest)
- Import same assertion libraries
Test Structure:
- If codebase uses table-driven tests, use that pattern
- If codebase uses describe/it blocks, use that pattern
- Match indentation and formatting
Assertions:
- Use same assertion style (require.Equal vs assert.Equal)
- Follow error message conventions
Mocking:
- Use same mocking library (mockery, jest.mock, unittest.mock)
- Follow interface/class mocking patterns found in codebase
Alternative: Use Test-Writer Agent
For complex test generation, spawn the test-writer agent:
Task(subagent_type="workflows:test-writer",
prompt="Generate tests for [functions] following patterns in testing.md.
Expected behavior: [describe].
Return test code only.")
Benefits:
- Conserves main agent context (3k instead of 20k+)
- Agent reads testing.md and examples in isolation
- Returns only the test code you need
- Follows project patterns automatically
When to use:
- Generating multiple test files
- Complex table-driven tests
- During phased implementation (see
spawn-implementation-agents)
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.
- 6d ago First seen · 135 lines · 25 tokens per session scan A 93bf7aff6337
follow-test-patterns is a skill published in the GitHub repository eveld/claude (10 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 753 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
implement
TDD implementation (RED→GREEN→REFACTOR) → verify → review.
testing
TDD/BDD testing principles. Use when writing tests, reviewing test coverage, setting up testing, or discussing test strategy and test architecture.
tdd-workflow
Test-driven development workflow.
ai-observability-promptfoo
Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation.
workflow-analysis
Workflow d'Analyse Obligatoire. Use when working with workflow analysis.
refactor-ops
Safe refactoring patterns - extract, rename, restructure with test-driven methodology and dead code detection. Use for: refactor, refactoring, extract function, extract component, rename, move file, restructure, dead code, unused imports, code smell, duplicate code, long function, god object, feature envy, DRY…