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/anilcancakir/claude-code-plugins/my_tddgit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginsWrote 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/anilcancakir/claude-code-plugins/my_tdd)<a href="https://agentmods.dev/commands/anilcancakir/claude-code-plugins/my_tdd"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code-plugins/my_tdd.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 | $0.00025 | $0.01007 |
| Opus 5 | $0.00013 | $0.00504 |
| Sonnet 5 | $0.00005 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
my_tdd 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 5d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/my_tdd - Test-Driven Development
Direct TDD workflow for immediate implementation. Enforces strict RED-GREEN-REFACTOR discipline.
Usage
/my_tdd [feature description]
Examples
/my_tdd user login endpoint
/my_tdd shopping cart add item functionality
/my_tdd password reset email service
/my_tdd order total calculation with discounts
What Happens
-
Detect Test Framework
- Identifies project stack (Laravel, Flutter, Vue)
- Selects appropriate test framework
- Locates test directories
-
Spawn TDD Enforcer Agent
- Uses Sonnet model for efficient test/code writing
- Strict RED-GREEN-REFACTOR enforcement
-
TDD Cycle (Repeats for Each Behavior)
RED Phase:
- Write a failing test
- Run test - MUST FAIL
- If passes, investigate (code may already exist)
GREEN Phase:
- Write minimal implementation
- Just enough to pass the test
- Run test - MUST PASS
REFACTOR Phase:
- Improve code quality
- Run tests after each change
- Tests MUST stay green
-
Iterate
- Identify next behavior to test
- Repeat cycle until feature complete
Framework Detection
| Stack | Test Framework | Test Directory |
|---|---|---|
| Laravel | PHPUnit/Pest | tests/ |
| Flutter | flutter_test | test/ |
| Vue (Vitest) | Vitest | src/**/__tests__/ |
| Vue (Jest) | Jest | tests/ or __tests__/ |
| Nuxt | Vitest | tests/ |
Test Types
Laravel
- Feature Tests (
tests/Feature/): HTTP requests, full request lifecycle - Unit Tests (
tests/Unit/): Isolated class testing, services
Flutter
- Unit Tests (
test/unit/): Business logic, services, models - Widget Tests (
test/widget/): UI components, interactions - Integration Tests (
test/integration/): Full app flows
Vue
- Unit Tests: Composables, utilities, stores
- Component Tests: Vue components with Vue Test Utils
Example Workflow
/my_tdd user registration
## RED Phase
Writing test: test_user_can_register_with_valid_data
File: tests/Feature/Auth/RegistrationTest.php
Running test...
FAILED (expected - RegisterController does not exist)
## GREEN Phase
Creating: app/Http/Controllers/RegisterController.php
Running test...
PASSED
## REFACTOR Phase
- Extracted validation to FormRequest
- Added PHPDoc comments
Running tests...
PASSED
## Cycle 2: RED Phase
Writing test: test_registration_fails_with_invalid_email
...
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.
- 5d ago First seen · 181 lines · 25 tokens per session scan A a855df14214c
my_tdd is a command published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 1,007 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 commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
health
Run the Self-Star Doctor - a green/yellow/red health board across all 7 junctions of the self- loop.
plan-new
Plan a complex project with discovery, structure, and kill criteria.
create-hook
Create a new custom automation hook.
remember
Explicitly save something to memory as an experience.
evolution
Show what the system learned and changed recently.