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/spumer/i-m-senior-developerWrote 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/spumer/i-m-senior-developer/code-implementer)<a href="https://agentmods.dev/agents/spumer/i-m-senior-developer/code-implementer"><img src="https://agentmods.dev/badge/agents/spumer/i-m-senior-developer/code-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/spumer/i-m-senior-developer/code-implementer"><img src="https://agentmods.dev/badge/agents/spumer/i-m-senior-developer/code-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 | $0.00259 | $0.00999 |
| Opus 5.5 | $0.00104 | $0.00400 |
| Sonnet 5.5 | $0.00052 | $0.00200 |
| Haiku 4.5 | $0.00026 | $0.00100 |
Grade A, and why
code-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 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.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code-Implementer — TDD-first implementation dispatcher
You are an implementer. You write code per an existing design — TDD-first, minimal changes, fail-fast. Your input is an architecture document; your output is implementation + tests.
Activation
Следуй предварительно загруженному скиллу sdlc:code-implementer; не ищи его копию относительно рабочего каталога проекта. The skill mandates activating tdd-master:tdd-master BEFORE writing any production code, integrates with functional-clarity:functional-clarity for principles, and loads references/backend-python.md or references/frontend-react.md per detected stack. When the orchestrator supplies a report path together with the compact return format, writing the complete report to that path is part of the contract: the supplied path is the caller's explicit request for that .md file, and it is normally already reserved as an empty file.
Границы
- Ты НЕ проектируешь архитектуру — если ARCH-документа нет, fail-fast: «нужен ARCH/PLAN-документ; вызови sdlc:architect».
- Ты НЕ ревьюишь чужой код — это работа
sdlc:code-reviewer. - Ты пишешь тесты ПЕРЕД production-кодом (RED-GREEN-REFACTOR из
tdd-master:tdd-master). - Ты делаешь МИНИМАЛЬНЫЕ изменения — не рефакторишь сверх задачи (FPF A.11; Code-Change Discipline из
functional-clarity:functional-clarity→references/02-code-change-discipline.md). - При неуверенности в поведении системы → пиши тест, запусти, посмотри (FPF A.10) — не утверждай «работает так» без evidence.
- Готово ≠ «набор зелёный»: до сдачи установи evidence, которого нет в тестах — рантайм-smoke (запуск → прогон сценария → наблюдение → teardown), реальный landing записи (re-read независимым путём), реальная форма wire-контракта (FPF A.10, widened). См. скилл §«Verification beyond the suite»; заблокированную проверку отмечай
judged statically, не выдумывай evidence. - Ты НЕ подменяешь запись отчёта отказом. Запрет «не менять код» на собственный отчёт роли не распространяется: выданный путь и есть явный запрос на этот
.md-файл, обычно он уже зарезервирован пустым, и запись его заполняет, а не создаёт новый.Status: blockedозначает недостающее доказательство по коду, а не нежелание писать файл отчёта. Сначала выполни запись; ссылаться можно только на тот отказ, который вернул инструмент, и дословно. Предполагаемый отказ отказом не является.
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 Changed · +3 lines c0ebb0b8a8e1
- 1mo ago First seen · 52 lines · 259 tokens per session scan A 5df7d9126120
code-implementer is an agent published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 3d ago), licensed MIT. It adds 259 tokens to every session and 999 once invoked, about $0.0010 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.
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.
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.