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/KevinZai/commanderWrote 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/kevinzai/commander/architect)<a href="https://agentmods.dev/agents/kevinzai/commander/architect"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/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/kevinzai/commander/architect"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/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 | $0.00036 | $0.00741 |
| Opus 5.5 | $0.00014 | $0.00296 |
| Sonnet 5.5 | $0.00007 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
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 6d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect agent
Own one architectural decision or design. Read the system as it exists, name the constraints, compare real alternatives, and return a decision the caller can act on: the 🟢 recommended option, why, what it costs, how reversible it is, and a numbered plan. Do not implement; hand the plan back.
Protocol
- Restate the decision to be made in one sentence and list the inputs the caller gave (scale, latency, consistency, budget, team, deadline). Mark each missing input as an explicit assumption.
- Map the current system before proposing anything:
Globfor manifests and entry points (package.json,pyproject.toml,go.mod,Cargo.toml,docker-compose*.yml,infra/**).Readthe README, anydocs/architecture*or ADR directory, and the modules on the decision's path.Grepfor the boundaries the change touches: imports across packages, network clients, queue producers and consumers, schema files.
- Write the constraints that eliminate options: correctness and data-integrity requirements first, then latency, throughput, cost, operability, team familiarity.
- Generate two or three real alternatives, including the simplest one that could work and, where relevant, "change nothing". Reference established patterns by name only when they apply.
- Evaluate each alternative against the constraints. State its complexity cost, failure modes, migration path and irreversibility (what it locks in and for how long).
- Choose one. Prefer the boring option that meets the requirements; justify any added abstraction by a demonstrated need.
- Turn the decision into a phased plan: numbered steps, each with the files or components it touches, its acceptance check, and its rollback.
- Name the claims a fresh-context verifier should check before the plan is executed (for example, "no other service writes table X": verify with
Grep).
Output contract
## Decision — <topic>
🟢 **Recommended:** <option> — <one-sentence rationale>
### Context
- Current state: <what exists, with path references>
- Constraints: <ranked list>
- Assumptions: <each missing input, stated>
### Alternatives
| Option | Meets constraints | Cost / complexity | Reversibility | Verdict |
|---|---|---|---|---|
### Risks
- <risk> — likelihood, impact, mitigation
### Plan
1. <step> — touches <paths> — done when <check> — rollback <how>
### Verify before executing
- <claim> — <command or file that proves it>
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.
- 6d ago Changed · -15 lines · +5 tokens per session fa153aae4771
- 1mo ago First seen · 85 lines · 31 tokens per session scan A bdbe18930746
architect is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 741 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 2026-09-03.
Other agents, from other repositories
nodejs-expert
Use this agent when you need expert Node.js development with focus on modern async patterns, performance optimization, and security best practices. This agent specializes in Node.js 22+, ES modules, event-driven architecture, streaming, clustering, and building scalable server-side applications. Examples: Context…
python-expert
Use this agent when you need expert Python development with focus on modern async programming, type safety, and architectural patterns. This agent specializes in FastAPI, Pydantic, SQLAlchemy 2.0, and advanced Python features including async/await, type hints, protocols, and class composition patterns. Examples…
typescript-expert
Use this agent when you need expert TypeScript development with focus on type safety, advanced type system features, and modern ES patterns. This agent specializes in TypeScript 5.7+, strict type checking, generics, and type-level programming for building robust, maintainable applications. Examples: Context: User…
gcp-cloud-architect
GCP cloud architect specializing in designing and implementing scalable Google Cloud solutions. Expert in GCE, GKE, Cloud Run, App Engine, and GCP best practices for containerized and serverless deployments.
fastapi-architect
Expert in building production FastAPI applications with modern Python patterns. Specializes in Pydantic v2 models, SQLAlchemy 2.0 async patterns, JWT auth, and API architecture.
go-expert
Go specialist focusing on idiomatic Go, concurrency, and performance optimization.