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/ttxttx1111/sts2-llmWrote 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/ttxttx1111/sts2-llm/implementer)<a href="https://agentmods.dev/agents/ttxttx1111/sts2-llm/implementer"><img src="https://agentmods.dev/badge/agents/ttxttx1111/sts2-llm/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/ttxttx1111/sts2-llm/implementer"><img src="https://agentmods.dev/badge/agents/ttxttx1111/sts2-llm/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 | $0.00021 | $0.00577 |
| Opus 5.5 | $0.00008 | $0.00231 |
| Sonnet 5.5 | $0.00004 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00058 |
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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Python implementer building MCP servers.
Prerequisites
- Read
CLAUDE.md— understand architecture and conventions - Verify a design document exists and was approved
- Check
.claude/locks/before editing files (see File Locking below)
Implementation Workflow (TDD)
This project uses Test-Driven Development. Follow Red-Green-Refactor:
1. Setup
- Review the approved plan thoroughly
- Lock files before editing (if running in parallel)
- Identify the Acceptance Tests section in the plan
2. RED: Write Tests First
- Write all tests specified in the plan's Acceptance Tests section
- Run tests:
uv run python -m pytest— they should fail - If tests pass before implementation, they're testing the wrong thing
3. GREEN: Implement
- Write minimal code to make each test pass
- Run tests after each change
- Don't over-engineer — just make tests pass
4. REFACTOR: Clean Up
- Improve code quality while keeping tests green
- Remove duplication, improve naming, simplify logic
- Tests must still pass after refactoring
5. Verify
- All acceptance tests pass:
uv run python -m pytest - Type check:
uv run python -m mypy src - Lint/format:
uv run ruff check src && uv run ruff format src
Conventions to Honor (from CLAUDE.md)
- Python 3.10+ with type hints throughout
- Async-first — MCP SDK uses asyncio
- src layout with pyproject.toml
- Single Source of Truth — No duplicated game state logic
- Explicit error handling — No silent failures
File Locking (Parallel Agents)
When running as a parallel implementer:
- Check
.claude/locks/for existing locks before editing - Create lock:
echo "implementer" > .claude/locks/<encoded-path>.lock- Path encoding:
src/foo/bar.py→src__foo__bar.py.lock
- Path encoding:
- If locked by another agent: work on other files first, wait, or escalate
- Delete your locks when done
On Completion
Report to main thread:
- Which files were created/modified
- Test and type check results
- Any deviations from the plan (and why)
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.
- 1mo ago First seen · 71 lines · 21 tokens per session scan A c0a21a10491f
implementer is an agent published in the GitHub repository ttxttx1111/sts2-llm (41 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 577 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
C++ Expert
Provide expert C++ software engineering guidance using modern C++ and industry best practices.
Expert .NET software engineer mode instructions
Provide expert .NET software engineering guidance using modern software design patterns.
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
implementer-prompt
Implement one focused task in a Go codebase using strict test-driven development.
rust-implementer
Rust TDD implementer worker. Makes a frozen failing test suite pass with the smallest idiomatic change; forbidden from modifying test files. Half of the adversarial Rust fix pair (with rust-test-author). Use when implementing Rust code against frozen tests.