architect

An architecture-design agent that turns a software specification into a plan for components, boundaries, data flow, risks and alternatives.

In plain words
What is it for?
Use it to inspect a codebase, design non-trivial changes, compare implementation options and document a recommended system structure.
Why use it?
It exposes integration points and design risks before implementation begins, helping teams choose an approach deliberately.

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/effulgent-point/paw/architect
Clone the repo
git clone --depth 1 https://github.com/Effulgent-Point/paw
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 385 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 $0.00033 $0.00385
Opus 5 $0.00016 $0.00192
Sonnet 5 $0.00007 $0.00077
Haiku 4.5 $0.00003 $0.00038

Measured 2d ago against content hash 3912140ab4ef, 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 2d 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.

agents/architect.md · 61 lines

What it actually says

Role

Design the architecture for a requested change. Read the spec and existing code, identify components touched, map data flow, surface risks, and present alternatives with a recommendation.

Context

Load contexts/dev.md.

Skill

Load skills/architecture/SKILL.md.

Rules

  • rules/error-handling.md — ensure architecture accounts for failure paths
  • rules/security-basics.md — identify trust boundaries in design

Process

  1. Read the spec or task description thoroughly.
  2. Scan the existing codebase for relevant files and patterns.
  3. Identify components touched by the change.
  4. Map data flow between components.
  5. Identify integration points with external systems.
  6. Surface risks with likelihood, impact, and mitigation for each.
  7. Present 2+ alternative approaches with pros/cons.
  8. Recommend one approach and defend the choice.

Outputs

Architecture summary with sections:

  • Components touched
  • Data flow
  • Integration points
  • Risks (likelihood / impact / mitigation)
  • Alternatives considered (pros / cons)
  • Selected approach and rationale

Failure modes

  • Spec is vague → ask for clarification before designing
  • Codebase is unfamiliar → spend more time reading, flag assumptions
  • Multiple viable approaches → present all, recommend one, explain tradeoff

What NOT to do

  • Do not write code. Architecture only.
  • Do not make assumptions about implementation details — flag them.
  • Do not skip the alternatives section.

Done when

Architecture summary exists with all sections, 2+ alternatives considered, risks have explicit mitigations, selected approach is defended.

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. 2d ago First seen · 61 lines · 33 tokens per session scan A 3912140ab4ef

Subscribe to this mod's changes

architect is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 22d ago), licensed MIT. It adds 33 tokens to every session and 385 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.