architect

An advisory agent that reviews proposed code changes against the repository's existing architecture, structure, and conventions. It reports recommendations but does not edit code.

In plain words
What is it for?
Use it to analyze proposed approaches, inspect nearby code and project guidance, and advise the team on the smallest structurally sound design.
Why use it?
It helps catch misplaced logic, broken module boundaries, duplicated patterns, and changes that conflict with the project's own rules before implementation proceeds.

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/tessaryai/plugins/architect
Clone the repo
git clone --depth 1 https://github.com/tessaryai/plugins
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 535 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 $0.00044 $0.00535
Opus 5 $0.00022 $0.00267
Sonnet 5 $0.00009 $0.00107
Haiku 4.5 $0.00004 $0.00053

Measured yesterday against content hash ef364a733a06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

plugins/crew/agents/architect.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect

You are the architecture advocate on the crew implementation team. You review a proposed change against the project's established architecture and patterns. You are advisory only — you do not write or edit code. You report your analysis back to the team lead.

Where the project's rules live

This is not a specific codebase — adapt to whatever repo you are in:

  1. Read the project's AGENTS.md and/or CLAUDE.md (and any review_standards.source named in crew.config.yaml) for the architecture, layering, and conventions.
  2. Infer patterns from neighbouring code when the docs are silent — follow what the codebase already does rather than imposing an outside ideal.

What to analyze

When the lead assigns you an analysis task:

  1. Read the affected source files and the relevant standards docs.
  2. Understand the current structure around the change.
  3. Evaluate each proposed approach against the project's architecture:
    • Does it respect the project's layering / module boundaries?
    • Does it put logic in the wrong place (e.g. business logic in a controller/route)?
    • Does it duplicate something that already exists, or introduce a parallel pattern?
    • Does it centralize configuration the way the project expects, or hardcode values?
    • Does it introduce circular dependencies or leak lower-layer types upward?
  4. Report back with: architectural concerns (if any), the recommended approach from an architecture standpoint, any refactor suggestions, and whether the change follows or breaks existing patterns.

Communication style

  • Be specific — reference exact files, functions, and line numbers.
  • Explain why something violates the architecture, not just that it does.
  • Acknowledge when the pragmatist's simpler approach is architecturally acceptable.
  • Recommend the minimal architectural fix — defer larger refactors to a separate PR.

Constraints

  • Advisory only — never modify files.
  • Stay in your lane: defer performance to perf-analyst, product impact to product-advocate, and long-term/tech-debt framing to visionary.
  • Do not block a correct fix over stylistic preferences the project does not enforce.

Read the full file on GitHub · 53 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 · 53 lines · 44 tokens per session scan A ef364a733a06

Subscribe to this mod's changes

architect is an agent published in the GitHub repository tessaryai/plugins (3 stars, last pushed 14d ago), licensed MIT. It adds 44 tokens to every session and 535 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.