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/refo/claude-dev-helpers/tddgit clone --depth 1 https://github.com/refo/claude-dev-helpersWhat 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 | $0.00045 | $0.01189 |
| Opus 5 | $0.00023 | $0.00594 |
| Sonnet 5 | $0.00009 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade B, and why
tdd scanned grade B 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Project helpers config (if present): !`cat .claude/helpers.json 2>/dev/null || echo "no helpers.json — infer test command from project files (package.json scripts, pyproject.toml, go.mod, Cargo.toml, Gemfile, etc.) and How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Driven Development
Context
- Project helpers config (if present): !
cat .claude/helpers.json 2>/dev/null || echo "no helpers.json — infer test command from project files (package.json scripts, pyproject.toml, go.mod, Cargo.toml, Gemfile, etc.) and ask the user to confirm before running"
Tooling
Use the project's test command. In order of preference:
commands.testfrom.claude/helpers.json- The script named
testinpackage.json/pyproject.toml/ equivalent - The conventional runner for the detected stack (e.g.
pytestfor Python,go test ./...for Go,cargo testfor Rust,mix testfor Elixir)
For watch mode, use commands.testWatch from helpers.json if present, otherwise the conventional watch invocation for the runner (e.g. --watch, pytest-watch, cargo watch -x test).
Test files should follow the conventions of the stack (*.test.ts, test_*.py, *_test.go, etc.) and be colocated with the code they test unless the project layout dictates otherwise.
Philosophy
Core principle: Tests should verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't.
Good tests are integration-style: they exercise real code paths through public APIs. They describe what the system does, not how it does it. A good test reads like a specification — "user can checkout with valid cart" tells you exactly what capability exists. These tests survive refactors because they don't care about internal structure.
Bad tests are coupled to implementation. They mock internal collaborators, test private methods, or verify through external means (like querying a database directly instead of using the interface). The warning sign: your test breaks when you refactor, but behavior hasn't changed. If you rename an internal function and tests fail, those tests were testing implementation, not behavior.
Anti-Pattern: Horizontal Slices
DO NOT write all tests first, then all implementation. This is "horizontal slicing" — treating RED as "write all tests" and GREEN as "write all code."
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.
- 2d ago First seen · 124 lines · 45 tokens per session scan B a71e0b7f2e64
tdd is a command published in the GitHub repository refo/claude-dev-helpers (2 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 1,189 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
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。.
go-test
Go TDD workflow with table-driven tests.
pm-auto-design2dev
設計レビューから実装完了まで完全自動化（設計レビュー→作業計画→TDD実装）.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
execute-plan
Execute an implementation plan methodically with TDD and continuous validation.
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.