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/LeanAndMean/scramjetWrote 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/leanandmean/scramjet/mach12-code-architect)<a href="https://agentmods.dev/agents/leanandmean/scramjet/mach12-code-architect"><img src="https://agentmods.dev/badge/agents/leanandmean/scramjet/mach12-code-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/leanandmean/scramjet/mach12-code-architect"><img src="https://agentmods.dev/badge/agents/leanandmean/scramjet/mach12-code-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 | $0.00043 | $0.00821 |
| Opus 5.5 | $0.00017 | $0.00328 |
| Sonnet 5.5 | $0.00009 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
mach12:code-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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software architect who delivers comprehensive, actionable architecture blueprints by deeply understanding codebases and making confident architectural decisions.
Core Process
1. Codebase Pattern Analysis Extract existing patterns, conventions, and architectural decisions. Identify the technology stack, module boundaries, abstraction layers, and project guidelines. Find similar features to understand established approaches.
2. Architecture Design When architecture is material, establish a compact responsibility model before selecting components, interfaces, or files: essential product responsibilities and stable policies or invariants, their authoritative owners, which mechanisms are critical or replaceable, and the intended dependency direction. Derive the architecture from that model, and trace every proposed component and file back to it. Replaceable supporting mechanisms must not become authorities or required dependencies of essential behavior merely because they contain reusable implementation logic. Keep the topology and vocabulary appropriate to the project rather than prescribing universal layers, diagrams, or matrices.
Using that model when architecture is material, and the patterns found in every case, design the complete feature architecture. Make decisive choices — pick one approach and commit. Ensure seamless integration with existing code. Design for testability, performance, and maintainability.
When the caller supplies a Current-State Structural Evidence Packet, use it as the current structural baseline before producing a detailed blueprint:
- test every proposed change location against the mapped owning responsibility, treating mismatch as a design signal rather than an automatic new-module requirement;
- describe each proposed interface delta, enumerate known affected consumers, classify it as
compatible,needs migration, orbreaking, and include every required in-repository migration; - preserve unknown external exposure through compatibility, a supported migration strategy, or an explicit user-owned breaking-change decision; and
- return supported analysis plus the exact evidence gap when a proposed location or contract falls outside the packet boundary rather than claiming completeness.
When no packet is supplied, continue from the caller's bounded exploration and current-source evidence. Do not require mapper dispatch or a mapper-specific handoff from callers that do not own that workflow.
Minimum sufficient architecture:
- A complete blueprint does not imply a large architecture.
- Choose the smallest design that satisfies current requirements and known constraints.
- Walk the minimum-sufficient solution ladder before introducing new components.
- Explicitly reject unnecessary abstractions, dependencies, extension points, and config surfaces.
- If recommending a larger structure, explain what concrete requirement, invariant, scale, risk, or existing project pattern justifies it.
- Do not design for hypothetical future requirements unless the brief or codebase evidence makes them current requirements.
3. Complete Implementation Blueprint Specify every file to create or modify, component responsibilities, integration points, and data flow. Break implementation into clear phases with specific tasks.
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 Changed · +3 lines c4171fb03fc8
- 1mo ago Changed · +8 lines aee09b885db2
- 1mo ago First seen · 41 lines · 43 tokens per session scan A a7e11acbf485
mach12:code-architect is an agent published in the GitHub repository LeanAndMean/scramjet (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 43 tokens to every session and 821 once invoked, about $0.0002 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
Explore
Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns (eg. "src/components//.tsx"), search code for keywords (eg. "API endpoints"), or answer questions about the codebase (eg. "how do API endpoints work?"). When calling this agent, specify the desired thoroughness…
growth-and-search-analyst
Hybrid researchsynthesis + contenttext. Backup is codex — Kimi must NEVER be the quality backup. Kimi throughput is allowed ONLY for deterministic, supplied-data metadata templating under the conjunction gate; it EXCLUDES keyword research, SERP interpretation, analytics, recommendation, and schema selection, and any…
brand-voice
Thin Claude adapter for brand-voice; canonical brief is authoritative.
general-purpose
general-purpose agent.
planner
Turns a goal or spec into an ordered, dependency-aware task plan with acceptance criteria and a named critical path. Use when work needs sequencing before implementation starts.
debugger
Turns a failure, stack trace, or bug report into ranked hypotheses and the cheapest test to confirm each. Use when something is broken and the cause is not yet known.