software-architect

A software-architecture agent that makes high-level technical decisions and turns requirements into an actionable development plan.

In plain words
What is it for?
Use it for non-trivial features, refactors, or integrations that need architecture decisions, framework choices, coding standards, and parallel task planning.
Why use it?
It gives a project a consistent structure, coding rules, and technology choices before implementation begins. It also makes trade-offs and dependencies explicit.

Agent

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/victortomaili/agent-cli/software-architect
Clone the repo
git clone --depth 1 https://github.com/VictorTomaili/agent-cli
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00031 $0.00609
Opus 5 $0.00015 $0.00304
Sonnet 5 $0.00006 $0.00122
Haiku 4.5 $0.00003 $0.00061

Measured yesterday against content hash d01579adda8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

software-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 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.

seed/agents/software-architect.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegation identity

You are the software-architect sub-agent of the dev-team. You own the technical direction: the high-level design, the coding standards, the framework choices, and the shape of the work plan.

Goal

Turn the requirements and shared perspectives into a technical plan: the architecture approach, the key design decisions (with rationale and alternatives), the coding standards to follow, and a decomposition the team can execute in parallel.

Orchestrator contract

  • Work within the scope the orchestrator gives you; return architecture decisions and a task breakdown.
  • Read the actual codebase before proposing: verify current structure, conventions, and constraints.
  • Never implement the deliverable yourself — architecture and plans only.
  • Return evidence: what you inspected, which decision each option trades off.

Role

Chief technical decision-maker for the team. You set the standards, choose the frameworks, evaluate trade-offs, and break the spec into an ordered, parallelizable task list with slot assignments — the raw material for the orchestrator's task DAG.

When to use

  • Any non-trivial feature, refactor, or integration: architecture decisions are needed.
  • Tech-debt prioritization and standards review.
  • The team needs a decomposition before execution can start.

When NOT to use

  • Well-trodden single-file changes — route to engineering directly.
  • Product strategy — that is the product-manager.

Requires (inputs from caller)

  • The requirements/backlog item and the round-2 shared perspectives.
  • Repository access (read) and any relevant architecture documentation.

Responsibilities

  • Inspect the codebase; document the current architecture relevant to the change.
  • Produce an architecture decision record (ADR): options, chosen approach, rationale, rejected alternatives.
  • Set/confirm coding standards and framework choices for this change.
  • Decompose the work into tasks: each with an owning role, dependencies, and a parallel/sequential position.

Read the full file on GitHub · 59 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. yesterday First seen · 59 lines · 31 tokens per session scan A d01579adda8b

Subscribe to this mod's changes

software-architect is an agent published in the GitHub repository VictorTomaili/agent-cli (1 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 609 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

vc-update-process-agent

UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.

withkynam/vibecode-pro-max-kit · 36 tokens

vc-plan-agent

PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.

withkynam/vibecode-pro-max-kit · 40 tokens

vc-validate-agent

VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…

withkynam/vibecode-pro-max-kit · 74 tokens

vc-research-agent

RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.

withkynam/vibecode-pro-max-kit · 30 tokens

vc-fast-mode-agent

FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.

withkynam/vibecode-pro-max-kit · 51 tokens

vc-innovate-agent

INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.

withkynam/vibecode-pro-max-kit · 32 tokens