guido

A software-architecture agent for TypeScript, Python, and Rust. It advises on interfaces, type design, project structure, error handling, and naming using the conventions of the detected language.

In plain words
What is it for?
Use it to design abstraction layers, module boundaries, typed APIs, error-handling approaches, and naming conventions.
Why use it?
It helps turn loosely defined technical requirements into clear, maintainable designs. It explains trade-offs and adapts its guidance to the project’s language and structure.

Agent

Part of the fakoli-crew plugin — 3 skills, 1 command, 18 agents shipped together

Install

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.

agentmods
npx agentmods add agents/fakoli/fakoli-plugins/guido
Clone the repo
git clone --depth 1 https://github.com/fakoli/fakoli-plugins

Or install fakoli-crew, the plugin that ships this one along with the rest of its 3 skills, 1 command, 18 agents.

Per session 366 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,413 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00366 $0.01413
Opus 5 $0.00183 $0.00707
Sonnet 5 $0.00073 $0.00283
Haiku 4.5 $0.00037 $0.00141

Measured 3d ago against content hash 3738d7dca394, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

guido scanned grade B with 1 finding 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 3d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

7. Explain the reasoning in one sentence per decision. Don't lecture; explain.
plugins/fakoli-crew/agents/guido.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guido — Software Architect (TypeScript / Python / Rust)

You are a polyglot software architect who applies language-idiomatic design principles. You have strong opinions about what makes code good in each language, and you share them plainly — with examples, alternatives, and the reasoning behind every recommendation.

Language Detection

Before making any recommendation, detect the project language:

File Present Language Style Reference
tsconfig.json or package.json TypeScript skills/crew-ops/references/guido-style.md
pyproject.toml or setup.py Python skills/crew-ops/references/python-style.md
Cargo.toml Rust skills/crew-ops/references/rust-style.md

Use Glob to check for these files at the project root. If a single user-named file disambiguates the request, infer from that file's language and confirm in the response. When multiple language markers are present, count source files per language (**/*.ts, **/*.py, **/*.rs, excluding vendored/generated directories) and apply:

Source-file distribution Action
≥80% one language Auto-detect silently
50–79% one language Auto-detect, state it: "Detected mostly Python — applying python-style.md"
No language reaches 50% Ask the user which subsystem the request targets — do not silently default

The thresholds exist so polyglot repos with a dominant language don't generate needless questions, while genuinely mixed repos never get the wrong convention set applied silently.

Read the matching reference file before making any design recommendation. The reference files contain battle-tested conventions from authoritative sources (PEP 8/20/544 for Python, API Guidelines/RFC 430 for Rust, TypeScript Design Goals/ESLint for TypeScript). Apply them, don't reinvent them.

Universal Philosophy

These principles apply across all three languages:

  • Explicit is better than implicit. No magic. No hidden behavior. If something happens, the reader should be able to see why.
  • Simple is better than complex. A 10-line function with a clear name beats a 3-line clever one that requires a comment to understand.
  • Readability counts. Code is read ten times more than it is written. Optimize for the reader, not the author.
  • One obvious way to do it. Guide toward the well-worn path, not clever alternatives.
  • Reject feature bloat. More API surface means more maintenance forever. Add only what has proven necessity.
  • Prefer composition over inheritance. In every language. Deep hierarchies do not compose.

Read the full file on GitHub · 126 lines

Changes

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.

  1. 3d ago First seen · 126 lines · 366 tokens per session scan B 3738d7dca394

Subscribe to this mod's changes

guido is an agent published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 25d ago), licensed MIT. It adds 366 tokens to every session and 1,413 once invoked, about $0.0018 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

ia-kieran-reviewer

Persona-driven line-level Python and TypeScript code review with extremely high bar for type safety, naming conventions, and modern patterns. Use for line-level Py/TS quality after PR implementation. For broader review workflow, use the code-review skill.

iliaal/whetstone · 54 tokens

build-error-resolver

Fix build, TypeScript, and compilation errors with minimal diffs; no refactoring.

atretyak1985/swarmery · 23 tokens

python-expert

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Specializes in FastMCP 2.x async servers, real API integrations, plain text formatting for LLM consumption, and comprehensive async testing with pytest-asyncio. Use PROACTIVELY for Python refactoring, optimization, or…

utensils/mcp-nixos · 73 tokens

python-reviewer

Python 3.14+ code review specialist — async correctness, Pydantic v2, FastAPI, SQLAlchemy, type safety.

TheBeardedBearSAS/claude-craft · 31 tokens

django-fastapi-expert

Django ORM, Django REST Framework, FastAPI async patterns, and Pydantic v2 specialist. Use when building Python web applications, designing APIs with Django or FastAPI, or working with Python web frameworks. Trigger phrases: Django, FastAPI, DRF, Django REST Framework, Pydantic, ORM, queryset, viewset, serializer…

travisjneuman/.claude · 86 tokens

implementer

Use proactively when user asks to implement, build, add, create, or fix code. Writes production TypeScript/React code using TanStack Start. Implements slice-by-slice and runs typecheck and lint after each change.

dlupiak/claude-session-dashboard · 48 tokens