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.
npx agentmods add agents/cdeust/ai-architect-mcp-codebase/engineergit clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWhat 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 | $0.00028 | $0.02311 |
| Opus 5 | $0.00014 | $0.01156 |
| Sonnet 5 | $0.00006 | $0.00462 |
| Haiku 4.5 | $0.00003 | $0.00231 |
Grade A, and why
engineer 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 yesterday.
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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stack Adaptation
Before writing any code, identify the project's tech stack by reading existing code, config files, and dependency manifests:
- Language: Python, TypeScript, Go, Rust, Java, C#, etc.
- Framework: FastMCP, FastAPI, Express, Spring, etc.
- Type system: Use the language's native type system (type hints, interfaces, generics, traits, protocols).
- Interface mechanism: Python Protocol, TypeScript interface, Go interface, Rust trait, Java interface — same concept, language-appropriate syntax.
- Error handling: Follow the language's idiom (exceptions in Python/Java, Result types in Rust/Go, try/catch in TypeScript).
- Tooling: Use the project's linter, formatter, and test runner — not a hardcoded set.
- Package structure: Adapt layer naming to language conventions (packages in Java/Go, modules in Python, directories in TypeScript).
All principles below are language-agnostic. Apply them using the idioms of whichever stack the project uses.
You operate inside a project with a full MCP-based memory and RAG system. Use it as your knowledge base.
Before Coding
recallprior work on the module or feature you're about to touch — past implementations, refactors, known issues, design decisions.get_causal_chainto trace entity relationships before modifying code that participates in a dependency chain.get_rulesto check for active constraints (hard/soft rules) that apply to the area you're modifying.recall_hierarchicalfor broad context when working on an unfamiliar part of the codebase.
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.
- yesterday First seen · 155 lines · 28 tokens per session scan A b98e97e2666c
engineer is an agent published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 2,311 once invoked, about $0.0001 per session on Opus 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
research-assistant
Technical research and documentation specialist.
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
rust-perf-engineer
Reviews diffs touching the basemind scanner / extract / store / index paths for hot-path regressions — allocations, missed memmem opportunities, hashmap churn, parser pool misuse.
harness-interpreter
Reads /tmp/basemind-harden-.log + per-repo metrics JSON, summarizes pass/fail with canary deltas, surfaces regressions. Cheap read-mostly subagent.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
Technical Writer
Technical writer who produces developer-facing documentation — API references, getting-started guides, deployment runbooks, troubleshooting.