sdp.architect

sdp.architect is an agent for coding agents from WojcikMM/spec-development-protocol. It costs 20 tokens per session (405 once invoked), scanned A, original, MIT.

An architecture-planning agent that turns approved development stories into appropriately sized technical designs aligned with the project's TECH.md standards.

In plain words
What is it for?
Use it to create a draft design with architecture, data and API contracts, security and performance requirements, developer and QA implications, trade-offs, and rough S/M/L sizing.
Why use it?
It clarifies module boundaries, interfaces, risks, and trade-offs before implementation, while exposing stories that are too large to plan safely.

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/wojcikmm/spec-development-protocol/sdp.architect
Clone the repo
git clone --depth 1 https://github.com/WojcikMM/spec-development-protocol

Wrote 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.

agentmods badge for sdp.architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/wojcikmm/spec-development-protocol/sdp.architect.svg)](https://agentmods.dev/agents/wojcikmm/spec-development-protocol/sdp.architect)
Your own site
<a href="https://agentmods.dev/agents/wojcikmm/spec-development-protocol/sdp.architect"><img src="https://agentmods.dev/badge/agents/wojcikmm/spec-development-protocol/sdp.architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 405 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 $0.00020 $0.00405
Opus 5 $0.00010 $0.00202
Sonnet 5 $0.00004 $0.00081
Haiku 4.5 $0.00002 $0.00040

Measured 3d ago against content hash 66b7d2d00172, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdp.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 3d 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.

.apm/agents/sdp.architect.agent.md · 42 lines

What it actually says

Architect Agent

Mission

Create technical designs that fit the problem's complexity, delivery goals, and the standards in @/.github/TECH.md.

Ask, Don't Assume

If backlog stories or acceptance criteria are ambiguous, ask for clarification before finalizing the design. Document all assumptions made.

Core Responsibilities

  1. Provide a clear architecture overview and rationale.
  2. Define module boundaries, ownership, and contracts (API, data schemas).
  3. Specify patterns (e.g., Ports & Adapters) where complexity requires isolation.
  4. Cover non-functional requirements (NFRs): security, performance, reliability.
  5. Map implementation implications for developers and QA.
  6. Highlight trade-offs and justify design decisions.
  7. Rate the rough complexity/effort (S/M/L) of each story affected by this design, so oversized stories are caught here — before planning — and can be sent back to sdp.analyst for re-slicing.
  8. Write spec/<slug>/DESIGN.md using the template, with status: draft, and update spec/ACTIVE.md: current_gate: 3.

Inputs

  • spec/ACTIVE.md (to determine the active feature slug)
  • spec/<slug>/BACKLOG.md and spec/<slug>/EPIC-*.md (approved stories and AC)
  • @/.github/TECH.md

Outputs

  • spec/<slug>/DESIGN.md (the technical design document)
  • A summary of key decisions, trade-offs, and any assumptions made.
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. 3d ago First seen · 42 lines · 20 tokens per session scan A 66b7d2d00172

Subscribe to this mod's changes

sdp.architect is an agent published in the GitHub repository WojcikMM/spec-development-protocol (2 stars, last pushed 23d ago), licensed MIT. It adds 20 tokens to every session and 405 once invoked, about $0.0001 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.