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 commands/wbern/agent-instructions/tdd-reviewgit clone --depth 1 https://github.com/wbern/agent-instructionsWrote 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/commands/wbern/agent-instructions/tdd-review)<a href="https://agentmods.dev/commands/wbern/agent-instructions/tdd-review"><img src="https://agentmods.dev/badge/commands/wbern/agent-instructions/tdd-review.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 | $0.00013 | $0.00940 |
| Opus 5 | $0.00006 | $0.00470 |
| Sonnet 5 | $0.00003 | $0.00188 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
tdd-review 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 4d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General Guidelines
Output Style
- Never explicitly mention TDD in code, comments, commits, PRs, or issues
- Write natural, descriptive code without meta-commentary about the development process
- The code should speak for itself - TDD is the process, not the product
Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).
Plan File Restriction
NEVER create, read, or update plan.md files. Claude Code's internal planning files are disabled for this project. Use other methods to track implementation progress (e.g., comments, todo lists, or external tools).
(If there was no info above, fallback to:
- Context of the conversation, if there's an immediate thing
bd readyto see what to work on next and start from there)
Test Quality Review
Analyze test files against FIRST principles and TDD best practices.
Phase 1: Scope
| Input | Action |
|---|---|
| No argument | Find all test files in project |
| File path | Analyze specific test file |
| Directory | Analyze tests in directory |
Detect test files using common patterns: *.test.*, *.spec.*, *.stories.*, __tests__/**
Also check for framework-specific patterns based on the project's languages and tools (e.g., *_test.go, *_test.py, Test*.java, *.feature for BDD).
Phase 2: Analysis
For each test file, check against these criteria:
Quality Criteria
FIRST Principles
| Principle | What to Check |
|---|---|
| Fast | Tests complete quickly, no I/O, no network calls, no sleep()/setTimeout delays |
| Independent | No shared mutable state, no execution order dependencies between tests |
| Repeatable | No Date.now(), no Math.random() without seeding, no external service dependencies |
| Self-validating | Meaningful assertions that verify behavior, no manual verification needed |
TDD Anti-patterns
| Anti-pattern | Detection Signals |
|---|---|
| The Liar | expect(true).toBe(true), empty test bodies, tests with no assertions |
| Excessive Setup | >20 lines of arrange code, >5 mocks, deep nested object construction |
| The One | >5 assertions testing unrelated behaviors in a single test |
| The Peeping Tom | Testing private methods, asserting on internal state, tests that break on any refactor |
| The Slow Poke | Real database/network calls, file I/O, hard-coded timeouts |
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.
- 4d ago First seen · 122 lines · 13 tokens per session scan A 909bbfc92a71
tdd-review is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 940 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 2026-08-30.
Other commands, from other repositories
tdd-refactor
TDDのRefactorフェーズを実行します。テストを通す実装が完了した後、コード品質の改善とリファクタリングを行います。.
tdd-requirements
TDD開発の要件整理を行います。機能要件を明確化し、テスト駆動開発のための準備を行います。.
spec-impl
Execute spec tasks using TDD methodology.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
verification-repair
PitWay: Bounded, approve-before-edit correction after every task is done.
task-discard
PitWay: Abandon a dispatched task's worktree without integrating.