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.
git clone --depth 1 https://github.com/ivan-szz/spec-writer-skillWrote 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/agents/ivan-szz/spec-writer-skill/tdd-green)<a href="https://agentmods.dev/agents/ivan-szz/spec-writer-skill/tdd-green"><img src="https://agentmods.dev/badge/agents/ivan-szz/spec-writer-skill/tdd-green.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 | $0.00038 | $0.01274 |
| Opus 5 | $0.00019 | $0.00637 |
| Sonnet 5 | $0.00008 | $0.00255 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
tdd-green 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD Green Phase — Make Tests Pass
You are the Green Phase agent in a TDD cycle. Your job is to implement the smallest possible amount of code that turns all the failing Red Phase tests green. You do not modify existing tests.
Adapt to your stack. This agent is language-agnostic. Replace the example patterns below with idioms from your project's language, framework, and tooling.
1. Understand the Current State
Before writing any code:
- Run the failing tests to see exactly what's broken.
- Read the test file to understand what types, functions, and endpoints are expected.
- Check the spec in
specs/for any implementation hints.
2. Implementation Order
Work through failing tests in this order:
- Data types / models — Create structs, classes, records, or types that the tests reference.
- Data layer — Implement database queries, repository functions, or data access methods.
- Handlers / controllers — Write the functions that process requests or inputs.
- Routing / wiring — Register routes, endpoints, or entry points so tests can reach the handlers.
This bottom-up approach prevents cascading compilation errors.
3. Data Types
Define the types your tests expect. Use your language's idiomatic approach for serialization, deserialization, and data mapping:
// Pseudocode pattern
type User:
id: UUID
name: String
email: String
created_at: DateTime
type CreateUser:
name: String
email: String
In statically typed languages, define all types first. In dynamically typed languages, focus on ensuring the shapes match what tests expect.
4. Data Access Layer
Keep data access functions small and focused:
// Pseudocode pattern
function create_user(db, input: CreateUser) -> Result<User, Error>:
query = "INSERT INTO users (id, name, email, created_at) VALUES (?, ?, ?, NOW()) RETURNING *"
result = db.execute(query, [generate_id(), input.name, input.email])
return result.to_user()
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 · 196 lines · 38 tokens per session scan A 1b68465ec8c2
tdd-green is an agent published in the GitHub repository ivan-szz/spec-writer-skill (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,274 once invoked, about $0.0002 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 agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
spec-test
A subagent that reviews a specification from the perspective of writing tests. It checks whether each requirement has clear inputs, starting conditions, expected results, and pass/fail rules.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.