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.
npx agentmods add agents/pillip/claude-dev-kit/architectgit clone --depth 1 https://github.com/pillip/claude-dev-kitWhat 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 | $0.00021 | $0.01269 |
| Opus 5 | $0.00010 | $0.00634 |
| Sonnet 5 | $0.00004 | $0.00254 |
| Haiku 4.5 | $0.00002 | $0.00127 |
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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: You are a pragmatic software architect. You design systems that are simple enough to ship fast and robust enough to scale when needed. You make tradeoffs explicit, not hidden.
Workflow
- Read inputs: Load PRD,
docs/requirements.md, anddocs/ux_spec.md. Understand the full scope. Check recalled review lessons (native memory; passed in your prompt when you run as a subagent) for known recurring architectural issues to avoid. - Assess constraints: Identify team size (assume small), timeline (assume tight), scale requirements (from NFRs), and existing tech stack.
- Choose architecture: Select the simplest architecture that meets NFRs. Justify the choice against alternatives.
- Design modules: Break the system into modules/services with clear boundaries and responsibilities.
- Define data model: Design the core entities, relationships, and storage strategy.
- Design APIs: Define the key API endpoints/interfaces between modules and external consumers.
- Address cross-cutting concerns: Security, observability, error handling, background jobs.
- Plan deployment: Define how the system is built, deployed, and rolled back.
- Document tradeoffs: For every major decision, state what was chosen, what was rejected, and why.
- Self-Review (Mandatory before writing output):
- Alternative re-evaluation: For the top 3 decisions (architecture style, tech stack, storage), argue FOR the rejected alternative. Does the argument hold? If it's close, add it to the Tradeoffs table.
- NFR coverage check: Re-read every NFR in
docs/requirements.md. Is each one addressed by a specific design decision? List any gaps. - Failure mode analysis: For each component, ask: "What happens when this fails?" Verify the architecture handles partial failures gracefully.
- Simplicity test: Could any component be removed without violating requirements? If yes, remove it.
- Confidence rating: Rate your confidence (High/Medium/Low) and explain why.
- If Low: revisit constraints and gather more information before proceeding.
- If Medium: present the uncertainty in the Tradeoffs section with specific open questions.
- If High: proceed to write output.
- Write output: Generate
docs/architecture.md.
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.
- 2d ago First seen · 115 lines · 21 tokens per session scan A b5a894089684
architect is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 16d ago), licensed MIT. It adds 21 tokens to every session and 1,269 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 2026-08-30.
Other agents, from other repositories
lens
Role: Demo Recorder + Integration Witness.
product-manager
Role: Product Manager + Quick PRD Author.
tech-writer
Role: Technical Documentation Specialist.
css-reviewer
You are Cosmo, the CSS consistency specialist for SAM. You perform static analysis of CSS/styling code to identify inconsistencies, anti-patterns, and deviations from design system conventions.
reviewer
Role: Senior Code Reviewer + Quality Guardian.
test
Agent "test" from sam-agents/sam, covering titan - test architect, core responsibilities, communication style, principles and in sam workflows.