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/VictorTomaili/agent-cliWrote 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/victortomaili/agent-cli/software-architect)<a href="https://agentmods.dev/agents/victortomaili/agent-cli/software-architect"><img src="https://agentmods.dev/badge/agents/victortomaili/agent-cli/software-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/victortomaili/agent-cli/software-architect"><img src="https://agentmods.dev/badge/agents/victortomaili/agent-cli/software-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 | $0.00031 | $0.00609 |
| Opus 5.5 | $0.00012 | $0.00244 |
| Sonnet 5.5 | $0.00006 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
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 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 — 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.
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 First seen · 59 lines · 31 tokens per session scan A d01579adda8b
software-architect is an agent published in the GitHub repository VictorTomaili/agent-cli (1 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 609 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 2026-08-31.
Other agents, from other repositories
code-reviewer
Reviews a diff or changed files after implementation for security, correctness, performance, and plan compliance. Use proactively after any significant code change, before declaring the task done. Read-only. Invoke with an explicit scope: the exact commits, files, or diff range that constitutes THIS session's change.
validation-engineer
Independently validates a trained model: metric correctness, holdout integrity, leakage, and whether the reported result survives scrutiny. Read-only on model and data code. Invoke with: the claimed result, the eval command, and the split definitions.
backend-engineer
Implements server-side logic: endpoints, business rules, persistence, and auth. Writes ONLY the paths assigned at dispatch. Safe to run in parallel with frontend-engineer when their paths are disjoint. Invoke with: the owned paths and the API contract it must publish.
data-engineer
Builds and fixes data loading, cleaning, splitting, and feature code for ML and pipeline work. Writes ONLY the paths assigned at dispatch. Invoke with: the owned paths, the input schema, and the contract the output must satisfy (columns, dtypes, row-count expectation).
frontend-engineer
Implements UI: components, pages, styling, and client-side state. Writes ONLY the paths assigned at dispatch. Safe to run in parallel with backend-engineer when their paths are disjoint. Invoke with: the owned paths, the API contract it consumes, and the states each view must handle.
ml-engineer
Implements model training, fine-tuning, and inference code. Writes ONLY the paths assigned at dispatch. Invoke with: the owned paths, the data contract produced upstream, the baseline to beat, and the compute budget.