design

A command that creates a System Design Document, a detailed explanation of how a software system should work. It chooses a topic-specific guide when one fits, such as guides for search engines, URL shorteners, or rate limiters.

In plain words
What is it for?
Use it to design systems, redirect services, search systems, rate limiters, or other software where traffic, data volume, response time, and architecture need to be reasoned about.
Why use it?
It gives design work a consistent structure and makes assumptions, scale, constraints, and unresolved questions visible. This helps produce a usable design even when some details are not yet known.

Command for Claude Code

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 commands/pierry/harness-kit/design
Clone the repo
git clone --depth 1 https://github.com/Pierry/harness-kit

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 664 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 $0.00035 $0.00664
Opus 5 $0.00017 $0.00332
Sonnet 5 $0.00007 $0.00133
Haiku 4.5 $0.00003 $0.00066

Measured 2d ago against content hash 3203891d402f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design 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.

.claude/commands/system-design/design.md · 47 lines

What it actually says

Design a system. Follow .claude/agents/system-architect/guides/pipeline.md for retry and approval, and .claude/shared/pipeline-pattern.md for inputs (resolve-mark-proceed) and eval (adversarial).

Inputs are resolved, not asked (resolve-mark-proceed). Resolve scale target (users / QPS / data / latency SLO), internal-vs-web-scale, and known constraints from any provided description plus context-library/. Infer a sensible order-of-magnitude scale and mark it ASSUMPTION: {x}; mark genuine unknowns NOT FOUND - NEEDS REVIEW: {detail} and keep going. The one permitted stop: if NO system or problem statement exists at all, ask once for the one-liner. Everything else resolves from context. Never stop to ask for a resolvable input.

Route to a topic skill if one fits. Check .claude/agents/system-architect/skills/{topic}/SKILL.md (currently: search-engine, url-shortener, rate-limiter). If the problem matches, use that skill's reference architecture. Otherwise use the generic skill .claude/agents/system-architect/skills/design/SKILL.md.

Compute feature_id = {YYYY-MM-DD}-{slug}.

Read:

  • .claude/agents/system-architect/guides/design-method.md
  • .claude/agents/system-architect/guides/writing-style.md
  • .claude/agents/system-architect/guides/templates/system-design.md
  • .claude/agents/system-architect/guides/pipeline.md
  • .claude/agents/system-architect/guides/examples/good-system-design-example.md
  • the matched topic skill, if any

Save to .claude/runtime/outputs/architect/design/{feature_id}.md.

Sensors: .claude/agents/system-architect/sensors/design-structure.md, .../sensors/design-rigor.md. Evals: .claude/agents/system-architect/evals/design-quality.md.

Run the evals adversarially: dispatch a fresh evaluator via the Task tool (subagent_type: general-purpose) that did not author this design. Hand it only the artifact path and the one rubric path; it scores against the rubric and reports the weighted total plus the low-scoring dimensions. Below threshold (8.0) retries per pipeline.md, regenerating only the flagged dimensions.

After save, reply with this exact shape (name the actual skill/sensors/evals/guides that ran):

Design saved at {path}. Score: {N}/10.
  skill:   {search-engine | design (generic)}
  sensors: design-structure ok, design-rigor ok
  eval:    design-quality {N}/10 (attempts: N)
  guides:  design-method.md, writing-style.md, templates/system-design.md
  canon:   {names applied}
  next:    /system-design:review
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 · 47 lines · 35 tokens per session scan A 3203891d402f

Subscribe to this mod's changes

design is a command published in the GitHub repository Pierry/harness-kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 664 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.