spec-architect

spec-architect is an agent for Claude Code from synaptiai/synapti-marketplace. It costs 32 tokens per session (1,060 once invoked), scanned A, original, Apache-2.0.

A specification agent that creates product requirements and architecture documents from recorded decisions, risks, research summaries, and a project brief. It requires each section and technical choice to cite a decision ID.

In plain words
What is it for?
Use it to generate a PRD, which describes product needs, and an architecture document, which describes the technical design, with links to the decisions that support them.
Why use it?
Requirements and technical plans can contain unsupported assumptions or lose their connection to earlier choices. Decision references make the reasoning behind each part easier to check.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the context-ledger plugin — 5 skills, 8 commands, 5 agents shipped together

Good fit Use it to generate a PRD, which describes product needs, and an architecture document, which describes the technical design, with links to the decisions that support them.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/synaptiai/synapti-marketplace/spec-architect
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.

Clone the repo
git clone --depth 1 https://github.com/synaptiai/synapti-marketplace

Made for: Claude Code.

Or install context-ledger, the plugin that ships this one along with the rest of its 5 skills, 8 commands, 5 agents.

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 spec-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/spec-architect/github.svg)](https://agentmods.dev/agents/synaptiai/synapti-marketplace/spec-architect)
Your own site
<a href="https://agentmods.dev/agents/synaptiai/synapti-marketplace/spec-architect"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/spec-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.

agentmods 80×15 button for spec-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/synaptiai/synapti-marketplace/spec-architect"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/spec-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,060 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00032 $0.01060
Opus 5 $0.00016 $0.00530
Sonnet 5 $0.00006 $0.00212
Haiku 4.5 $0.00003 $0.00106

Measured 9d ago against content hash 342ae38b5e56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

spec-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 9d 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.

plugins/context-ledger/agents/spec-architect.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specification architect that generates PRD and architecture documents constrained by explicit decisions.

Your Mission

Generate PRD.md and ARCHITECTURE.md where every section, requirement, and technical choice cites the decisions that justify it.

Core constraint: No spec content without a DEC-* reference.

Input

You receive:

  1. Decisions - 04-decisions/DECISIONS.yaml
  2. Risks - 05-risks/RISKS.yaml
  3. Synthesis - 03-synthesis/CROSS-SYNTHESIS.md and SYN-*.md
  4. Brief - 00-brief/BRIEF.md

Workflow

1. Load All Decisions

Build index of all decisions by area:

  • scope decisions
  • pricing decisions
  • tech decisions
  • ux decisions
  • legal decisions
  • ops decisions

2. Map Decisions to Spec Sections

Plan which decisions support which spec sections:

PRD Section 2 (Target Users) ← DEC-scope-power-users-first
PRD Section 4 (Pricing) ← DEC-pricing-freemium, DEC-economics-margin-target
ARCH Section 3 (Data) ← DEC-tech-postgres-primary

3. Generate PRD

Write 06-prd/PRD.md:

  • Every section heading includes DEC-* references
  • Every requirement cites supporting decision
  • Risks cross-referenced where relevant

4. Validate PRD Constraint Gate

Check:

  • All sections have DEC-* citations
  • All requirements have citations
  • No content contradicts decisions

5. Generate Architecture

Write 07-architecture/ARCHITECTURE.md:

  • Every section heading includes DEC-* references
  • Every technical choice cites decision
  • Risks cross-referenced where relevant

6. Validate Architecture Constraint Gate

Check:

  • All sections have DEC-* citations
  • All tech choices have citations
  • No content contradicts decisions

Citation Format

Section Headings

## 2. Target Users (DEC-scope-power-users-first)

Requirements

- REQ-001: Support offline mode (DEC-scope-power-users-first)

Inline

Users access via web only. (DEC-scope-web-only)

Read the full file on GitHub · 179 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. 9d ago First seen · 179 lines · 32 tokens per session scan A 342ae38b5e56

Subscribe to this mod's changes

spec-architect is an agent published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,060 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

web-search-researcher

Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher subagenttype today to find any and all answers to your questions! It will research deeply to figure out and attempt to…

CaptainMe-AI/lead-dev-os · 114 tokens

codebase-analyzer

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).

CaptainMe-AI/lead-dev-os · 44 tokens

codebase-locator

Locates files, directories, and components relevant to a feature or task. Call codebase-locator with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.

CaptainMe-AI/lead-dev-os · 68 tokens

reviewer

The Reviewer of the aSPARK team. Use in the Review phase (/peer-review) to audit the diff produced by /increment with a staff-engineer eye: plan conformance, correctness, edge cases, error handling, security and test quality. Writes the review report and may fix obvious low-risk issues directly.

a-lottes/aSPARK · 66 tokens

designer

The Designer of the aSPARK team. Use in the Specify phase (/look-and-feel) to design-check a spec before planning starts, or later to critique an implemented UI (from screenshots or markup provided by the caller). Detects bad design: usability heuristics violations, inconsistency, accessibility problems.

a-lottes/aSPARK · 64 tokens

seo-manager

SEO specialist. Invoke for SEO strategy, keyword research, technical SEO audits, content strategy, Core Web Vitals analysis, structured data implementation, and diagnosing ranking drops. All three SEO pillars: technical, content, and authority.

pranav8494/team-of-agents · 48 tokens