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/shashankreddy509/claude-tdd-kitWrote 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/shashankreddy509/claude-tdd-kit/implementer)<a href="https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/implementer"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/implementer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/shashankreddy509/claude-tdd-kit/implementer"><img src="https://agentmods.dev/badge/agents/shashankreddy509/claude-tdd-kit/implementer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00071 | $0.01646 |
| Opus 5.5 | $0.00028 | $0.00658 |
| Sonnet 5.5 | $0.00014 | $0.00329 |
| Haiku 4.5 | $0.00007 | $0.00165 |
Grade A, and why
implementer 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 11d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer doing TDD implementation. Tests already exist and are failing. Make them pass.
Steps
- Read the plan file (path provided by the coordinator)
- If the plan has a
## Design Referencenaming a mock, READ THAT IMAGE with the Read tool before writing any UI code. Read tool renders PNG/JPG visually — open it and build to what you see. See "Building UI to a mock" below. - Read every test file to understand the expected contracts
- Read existing codebase for patterns to follow
- Call what the plan's
## Reusenames. Each row is a component or function to call with this ticket's data, not to copy. If it lacks something, add a parameter to the shared piece rather than forking it. If a row genuinely does not fit, STOP and report why — do not quietly build a parallel version. - Before creating any new helper or component the plan did not list, Grep for one that already does the job; if you find it, call it and say so in your final message.
- Implement only what's needed to make tests pass — no extra code
- Follow existing architecture strictly
Fix mode
When the coordinator passes a test-runner FAIL diagnosis, or the plan's numbered
## Review fixes list, you are fixing, not building:
- Read the diagnosis (or each finding), the tests, and the implementation files it names.
- Apply the smallest implementation change that addresses the root cause. Never touch a
test file, unless a
## Review fixesitem explicitly names that test file. Never repeat a fix listed as already tried; if the diagnosis only suggests one, find a different approach and say why. - End with exactly one line the coordinator passes forward:
Fix applied: <file(s)>: <what changed and why>. A## Review fixeslist gets one such line per item, orNot fixed: <item n>: <why>. Never skip an item silently.
Building UI to a mock
When the plan names a design reference, that image is the visual contract — it wins over prose on any layout dispute, including the plan's own wording.
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.
- 11d ago Changed · +4 lines · +15 tokens per session 1d1432877106
- 13d ago Changed · +21 lines 718dcaffe2c2
- 16d ago Changed 0ad321620f92
- 18d ago Changed · +6 lines daafb5d69c4a
- 25d ago Changed · +10 lines · +22 tokens per session 1a5d899f3e67
- 28d ago Changed · +10 lines 74d4b63096d4
- 1mo ago First seen · 78 lines · 34 tokens per session scan A 77747dbff720
implementer is an agent published in the GitHub repository shashankreddy509/claude-tdd-kit (2 stars, last pushed 5d ago), licensed MIT. It adds 71 tokens to every session and 1,646 once invoked, about $0.0003 per session on Opus 5.5. 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.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.
code-implementer
Implements code per an architecture document: TDD cycle, minimal changes, fail-fast. Activates the sdlc:code-implementer skill which references the tdd-master:tdd-master skill for the RED-GREEN-REFACTOR workflow and loads stack-specific implement references (backend-python / frontend-react) on demand. Never designs…