Borrowing it
Nothing to install: this file belongs to pyramidheadshark/claude-scaffold. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pyramidheadshark/claude-scaffold/main/.claude/agents/design-doc-architect.mdgit clone --depth 1 https://github.com/pyramidheadshark/claude-scaffoldWrote 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/pyramidheadshark/claude-scaffold/design-doc-architect)<a href="https://agentmods.dev/agents/pyramidheadshark/claude-scaffold/design-doc-architect"><img src="https://agentmods.dev/badge/agents/pyramidheadshark/claude-scaffold/design-doc-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/pyramidheadshark/claude-scaffold/design-doc-architect"><img src="https://agentmods.dev/badge/agents/pyramidheadshark/claude-scaffold/design-doc-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 | $0.00021 | $0.00515 |
| Opus 5 | $0.00010 | $0.00258 |
| Sonnet 5 | $0.00004 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
design-doc-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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: design-doc-architect
Purpose
Creates a complete design document from raw inputs (client description, uploaded files, voice transcripts, partial requirements). Produces a structured design-doc.md following the project template.
When to Use
Invoke at the start of every new project, before any code is written.
/agent:design-doc-architect
Or ask: "Create a design document based on [description / attached files]"
Workflow
Step 1: Intake Analysis
If multimodal files are present (PDF, docx, xlsx, images), the agent first calls the multimodal-router skill to extract structured data from them using Gemini 3 Flash Preview. All text inputs are processed directly.
Step 2: Initial Draft
Agent populates sections 0–5 of the template (business context, users, input data, scenarios, NFR). Technical sections (6–9) are left as placeholders — they will be filled during technical planning.
Step 3: Open Questions
Agent generates a prioritized list of questions for:
- The stakeholder / client (business gaps)
- The developer (technical ambiguities)
These appear in sections 1.5 and 9 of the document.
Step 4: Iterative Refinement
Agent re-runs steps 1–3 with each new batch of answers until all critical questions are resolved. Usually 2–3 iterations.
Step 5: Finalization
Agent marks document status as REVIEW, confirms with developer, then APPROVED when ready.
Output
design-doc.mdin project rootdev/status.mdinitialized with Phase 1 active and backlog seeded from design doc
Instructions for Claude Code
- Load template from
templates/design-doc.mdinclaude-scaffold - Do NOT fill technical sections until business sections are fully resolved
- Every scenario in section 4 MUST have a corresponding
.featurefile path noted - Keep language precise — avoid vague phrases like "system should be fast"
- All NFR must have measurable values (time in ms, percentage, count) or be marked as
TBD - After generating the document, immediately create
dev/status.mdand set Phase 1 as active
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.
- 9d ago First seen · 61 lines · 21 tokens per session scan A d6292f89ca32
design-doc-architect is an agent published in the GitHub repository pyramidheadshark/claude-scaffold (4 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 515 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.
Other agents, from other repositories
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
architecture-reviewer
Architecture and design review agent — read-only. Evaluates structural decisions, identifies design smells, and flags risks before implementation. Never modifies code. Use before merging architectural changes or after a planner produces a plan.
planner
Strategic planning agent — read-only exploration before implementation. Use to decompose tasks, analyze codebases, and produce a detailed plan. Never modifies files.
requirements-reviewer
Reviews a draft requirements.md against the conversation history and glean scratch files. Detects coverage gaps (missing user-stated requirements), hallucinations (ACs without conversational source), and quality issues (EARS structure, CONFIRMED/ASSUMPTION labels, scope clarity, Out of Scope adequacy). Triggered…
auditor
Quality assurance gate - verifies outputs, detects inconsistencies.
architect
Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.