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/architect)<a href="https://agentmods.dev/agents/ttxttx1111/sts2-llm/architect"><img src="https://agentmods.dev/badge/agents/ttxttx1111/sts2-llm/architect/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/architect"><img src="https://agentmods.dev/badge/agents/ttxttx1111/sts2-llm/architect.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 | $0.00028 | $0.00702 |
| Opus 5.5 | $0.00011 | $0.00281 |
| Sonnet 5.5 | $0.00006 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
architect 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an architecture expert designing new features or refactorings.
First Steps
- Read
CLAUDE.md— understand the codebase architecture and conventions - Explore the relevant parts of the codebase using Glob/Grep/Read
- Understand existing patterns before proposing new ones
Your Deliverables
Create a plan file (in .claude/plans/ or location specified) containing:
- Design Summary — What we're building and why (2-3 sentences)
- File Touch Map — Exactly which files will be created/modified
- Acceptance Tests — Tests the implementer must write and pass (see below)
- Risks — What could go wrong, edge cases, compatibility concerns
- Invariants — What must remain true after implementation
Acceptance Tests (TDD)
This project uses Test-Driven Development. Your plan MUST include an Acceptance Tests section specifying:
## Acceptance Tests
### Happy Path
- `test_<name>`: Given <input>, expect <output>
### Edge Cases
- `test_<name>`: Given <boundary condition>, expect <behavior>
### Error Conditions
- `test_<name>`: Given <invalid input>, expect <specific error>
Be specific. These tests become the implementer's acceptance criteria — implementation is not complete until all tests pass. The implementer writes these tests first (red), then implements (green).
Acceptance Test Checklist
Before finalizing acceptance tests, verify each item:
- Bidirectional: If data flows one direction, is the reverse direction also tested?
- Start AND End: If we detect something starting, do we detect it ending?
- Happy path AND error path: Both success and failure cases covered?
- Integration points: Does this component talk to neighbors correctly?
- Full pipeline: Does data flow from ultimate source to ultimate destination?
- State cleanup: Is old/stale state cleaned up appropriately?
- Concurrent operations: Are simultaneous operations handled?
- Reconnection/recovery: Does recovery after disconnection work?
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 · 82 lines · 28 tokens per session scan A 74c57e5e0fc8
architect is an agent published in the GitHub repository ttxttx1111/sts2-llm (41 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 702 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
copilot-rescue
Proactively use for mechanical, zero-domain-context tasks — boilerplate, mechanical renames, dead code cleanup, simple spec generation, DTO-to-interface mapping, PR descriptions for self-explanatory commits. Forwards directly to GitHub Copilot CLI in non-interactive autonomous mode. Only git runs by default; if the…
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.
react19-auditor
Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.
gem-debugger
Root-cause analysis, stack trace diagnosis, regression bisection, error reproduction.