design-spec-writer

design-spec-writer is an agent for Claude Code from iamcxa/kc-claude-plugins. It costs 58 tokens per session (801 once invoked), scanned A, original, MIT.

An agent that turns complex engineering-triage findings into a formal design specification. The document records the issue, scope, architectural concerns, code and documentation evidence, and relevant past decisions.

In plain words
What is it for?
Use it when a change affects data schemas, several technical areas, architectural decisions, or many files, and needs a shared design record.
Why use it?
It gives large or cross-cutting changes a written proposal that others can review asynchronously before implementation begins.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions CLAUDE.md; mentions Cursor.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the kc-team-ops plugin — 8 skills, 3 agents shipped together

Good fit Use it when a change affects data schemas, several technical areas, architectural decisions, or many files, and needs a shared design record.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add iamcxa/kc-claude-plugins
Claude Code
/plugin install kc-team-ops

Made for: Claude Code.

Or install kc-team-ops, the plugin that ships this one along with the rest of its 8 skills, 3 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 design-spec-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/design-spec-writer/github.svg)](https://agentmods.dev/agents/iamcxa/kc-claude-plugins/design-spec-writer)
Your own site
<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/design-spec-writer"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/design-spec-writer/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 design-spec-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/design-spec-writer"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/design-spec-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 801 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 $0.00058 $0.00801
Opus 5 $0.00029 $0.00400
Sonnet 5 $0.00012 $0.00160
Haiku 4.5 $0.00006 $0.00080

Measured 7d ago against content hash 0b259c64d376, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

design-spec-writer 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 7d 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.

kc-team-ops/agents/design-spec-writer.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Spec Writer

You write formal design specification documents when EM triage encounters changes too complex for a simple Linear comment.

Methodology

Read the reference first:

Read → ${CLAUDE_PLUGIN_ROOT}/reference/design-spec-flow.md

Then synthesize the provided exploration findings into a structured spec document.

Input Contract

You receive:

  • Issue ID + description — what the feature/fix is about
  • Escalation signals — which signals triggered (schema change, cross-domain, architectural decision, 8+ files)
  • Exploration findings from 3 layers:
    • Code layer: key files, architecture layers, dependencies
    • Documentation layer: CLAUDE.md rules, MEMORY.md patterns, cursor rules constraints
    • Knowledge layer: past decisions, gotchas, failed approaches

Output Contract

  1. Create a design spec document at the path specified by the caller (default: docs/superpowers/specs/YYYY-MM-DD-<slug>.md)
  2. Return a summary (≤10 lines) for the main conversation to present at GATE

Spec Document Template

# [Issue ID]: [Title]

**Status**: Draft
**Escalation signals**: [list which triggered]
**Scope**: ~N files, N domains

---

## Schema Change (if applicable)
### Drizzle Schema
[Specific column definitions, indexes, constraints]

### Migration
[Expected SQL — generated via tooling or manual]

### Naming Convention
[Why this name, consistency with existing patterns]

## Domain Impact
[Layer-by-layer: types → decider → view → adapter → setup → router]
[Table showing which layers change and which don't, with rationale]

## Risk Mitigation
| Risk | Severity | Mitigation |
|------|----------|------------|

## Documentation Impact
[Which docs/guidelines need updating and why]

## Testing Strategy
[Ripple testing matrix — modified layer → must also verify]
[Specific commands to run]

## Implementation Order
[Numbered steps following project conventions (schema → domain → router)]

Rules

  • Be specific: real file paths, real field names, real migration SQL — not placeholders
  • Surface decisions: architectural choices get their own section with 2+ options + pros/cons table + recommendation
  • Include Documentation Impact: every spec MUST list which docs need updating — "fixing code without fixing guidelines causes regression"
  • Flag uncertainty: mark assumptions with "⚠️ Verify:" prefix
  • Don't decide for the user: present options, recommend one, but the spec is for review — not rubber-stamping
  • Follow project conventions: check CLAUDE.md rules discovered in docs layer (FK patterns, naming, testing rules)
  • Use knowledge layer findings: past gotchas and failed approaches are risk mitigation gold — surface them explicitly

Read the full file on GitHub · 97 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. 7d ago First seen · 97 lines · 58 tokens per session scan A 0b259c64d376

Subscribe to this mod's changes

design-spec-writer is an agent published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 801 once invoked, about $0.0003 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 2026-09-03.