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 majiayu000/spellbook --skill comprehensive-testinggit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/comprehensive-testing)<a href="https://agentmods.dev/skills/majiayu000/spellbook/comprehensive-testing"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/comprehensive-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 | $0.00057 | $0.02621 |
| Opus 5 | $0.00028 | $0.01311 |
| Sonnet 5 | $0.00011 | $0.00524 |
| Haiku 4.5 | $0.00006 | $0.00262 |
Grade A, and why
comprehensive-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 7d 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 — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comprehensive Testing
Based on Anthropic's Claude Code Best Practices and community patterns
Core Philosophy
"Claude performs best when it has a clear target to iterate against—a test case provides concrete success criteria."
Testing is not about proving code works; it's about designing code that is testable and documenting expected behavior.
Test Pyramid
/\
/ \ E2E Tests (10%)
/----\ - Full user flows
/ \ - Slowest, most brittle
/--------\
/ \ Integration Tests (20%)
/------------\ - Component interaction
/ \ - Real dependencies
/----------------\
Unit Tests (70%)
- Single function/method
- Fast, isolated, many
| Level | Speed | Scope | When to Use |
|---|---|---|---|
| Unit | <10ms | Single function | All logic |
| Integration | <1s | Multiple components | APIs, DB |
| E2E | <30s | Full flow | Critical paths |
TDD Workflow (Anthropic Recommended)
The 6-Step Process
1. WRITE TESTS FIRST
↓
2. VERIFY TESTS FAIL
↓
3. COMMIT TEST SUITE
↓
4. IMPLEMENT CODE
↓
5. VERIFY WITH SUBAGENT
↓
6. COMMIT IMPLEMENTATION
Step 1: Write Tests First
Be EXPLICIT about TDD to avoid mock implementations:
"I want to implement [feature] using TDD.
First, write tests for [expected behavior] with these input/output pairs:
- Input: X → Expected: Y
- Input: A → Expected: B
Do NOT create any implementation yet."
Step 2: Verify Tests Fail
# Run tests and confirm they fail for the RIGHT reason
npm test # or pytest, go test, etc.
# Expected: "function not found" or "undefined"
# NOT: syntax error, wrong import
Step 3: Commit Test Suite
git add tests/
git commit -m "test: Add tests for [feature] (RED phase)"
Step 4: Implement Incrementally
"Now implement the code to make these tests pass.
Do NOT modify the tests.
Run tests after each change until all pass."
What ships with it
1 file 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.
- 7d ago First seen · 454 lines · 57 tokens per session scan A 7e2748e63bcd
comprehensive-testing is a skill published in the GitHub repository majiayu000/spellbook (272 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 2,621 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
base
Universal coding patterns, constraints, TDD workflow, atomic todos.
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
coding-flow
Light coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
coding-agents-prompting-flow
Workflow for authoring and adapting AI-agent prompts: skills, agents, workflows, rules, etc.
bug-fix
Regression-first workflow for fixing a defect whose cause is known. Reproduce the confirmed defect, fix the root cause minimally, protect it with a regression test, and verify. If the root cause is still unknown, use the debugging skill first.
test-sweep
Run all test suites (unit, integration, API, E2E) and aggregate results into a summary report. Use after completing execution slices or before the Review Gate.