c-design

c-design is a skill for Claude Code from sentasity/cadence. It costs 109 tokens per session (3,756 once invoked), scanned A, original, MIT.

A design-folder generator turns a short overview document into a complete set of ordered design documents, including optional sections and an out-of-scope document.

In plain words
What is it for?
Use it to expand a draft product or software design into a structured folder with plain-English explanations, topic documents, optional infrastructure or architecture sections, and mockup placeholders.
Why use it?
It removes the need to create and organize each design document by hand. It can also pause after each document so you can review and correct the overview when inconsistencies appear.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents; names the AskUserQuestion tool.

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 cadence plugin — 11 skills, 5 agents, 1 hook shipped together

Good fit Use it to expand a draft product or software design into a…

Compare 6 skills 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 sentasity/cadence
Claude Code
/plugin install cadence

Made for: Claude Code.

Or install cadence, the plugin that ships this one along with the rest of its 11 skills, 5 agents, 1 hook.

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 c-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/sentasity/cadence/c-design.svg)](https://agentmods.dev/skills/sentasity/cadence/c-design)
Your own site
<a href="https://agentmods.dev/skills/sentasity/cadence/c-design"><img src="https://agentmods.dev/badge/skills/sentasity/cadence/c-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,756 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 $0.00109 $0.03756
Opus 5 $0.00055 $0.01878
Sonnet 5 $0.00022 $0.00751
Haiku 4.5 $0.00011 $0.00376

Measured 6d ago against content hash c66079a85530, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

c-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 6d 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.

skills/c-design/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/c-design

You materialize a design folder from the 00-overview.md stub. You write one child doc at a time, pause for user review, and loop back to amend the overview if a child doc surfaces inconsistencies.

Entry contract

Requires: the design artifact for {yyyy-mm-dd-slug} exists — check via skills/_shared/storage-resolution.md (artifact_exists) — and its 00-overview, read via read_artifact, carries status: draft and a populated Doc index; do not assume a <paths.designs>/…/00-overview.md file path.

Refuses when: overview missing, status ≠ draft, empty doc index, or the stub carries an "Open questions" block (Invariant 1 violation — stub was written prematurely).

Folder layout (every design)

<paths.designs>/
  {yyyy-mm-dd-slug}/
    00-overview.md
    00a-plain-english.md
    01-<topic>.md, 02-…
    95-visual-contract.md            # opt-in
    mockups/01-<slug>.html, 02-…     # with 95; default location, see mockups.dir
    97-infrastructure-inventory.md   # opt-in
    98-architecture-diagrams.md      # opt-in
    99-out-of-scope.md

Reserved slots: 00-overview, 00a-plain-english, 95-visual-contract, 97-infrastructure-inventory, 98-architecture-diagrams, 99-out-of-scope. Refuse to scaffold conflicting names (a conflicting 95-* name included). Each slot is materialized per skills/_shared/storage-resolution.md (write_doc), which the layer maps to a <slot>.md file on the filesystem backend and to a titled sub-page on the notion backend; the folder layout above is the filesystem view only.

Frontmatter

See skills/_shared/frontmatter.md. Design overview carries lifecycle; child docs carry only title:.

Writing flow

  1. Read the stub via skills/_shared/storage-resolution.md (read_artifact). List the proposed doc index. When the overview describes significant user-facing UI/UX work and the doc index lacks 95-visual-contract, offer the slot in the same confirmation (see Visual contract and mockups); when significance is genuinely unclear, ask; a mostly-backend design with an incidental UI touch gets no offer. Confirm with user: "Write 00a-plain-english.md next, then 01-<x>, 02-<y>. Sound right?" Then ask the generation-mode question (see Generation mode). Config values (authoring.*) come from running node "${CLAUDE_PLUGIN_ROOT}/scripts/resolve-config.js" (contract in skills/_shared/config-resolution.md; never read config files directly).
  2. Write child docs per chosen mode. Each doc is written to its reserved slot per skills/_shared/storage-resolution.md (write_doc); do not open or path-compute a <paths.designs>/…/<slot>.md file.
    • All-at-once: dispatch one fresh generator agent per technical child doc in parallel (up to authoring.max_parallel). Every generator prompt names the resolved storage backend and the matching syntax reference: skills/_shared/obsidian-format.md always, plus skills/_shared/notion-translation.md when the backend is notion (so generators author callouts as native <callout> blocks, not obsidian syntax). After all complete, dispatch cadence-doc-consistency once over the set for a consistency sweep (see Generation mode). Then generate 00a-plain-english.md last.
    • One-by-one: write one child doc, then proceed to step 3.
    • Inline: the main session writes every technical child doc itself, sequentially, via write_doc — no generator sub-agents, no per-doc pause, no cadence-doc-consistency sweep (a single author holds the whole context; Invariant 2 still applies in full). Then generate 00a-plain-english.md last and continue at step 8.
  3. Pause after each doc (one-by-one mode only). "<filename> written. Review and tell me to continue, revise, or stop." Never auto-write the next file in this mode. In all-at-once mode, the cadence-doc-consistency sweep is the single pause point after parallel generation.
  4. Invariant 2 — consistency re-litigation. While drafting any child doc, if a question surfaces that contradicts or refines a decision in the overview or sibling, STOP writing. Surface the conflict. Ask the user to resolve. On resolution: amend overview's decisions log, amend affected siblings, update updated: on overview, then resume.
  5. OOS additions during design. Any decision-not-to-do lands in 99-out-of-scope.md immediately with rationale + wikilink. Never deferred.
  6. 00a-plain-english.md is written last. Sections (in order): What this feature does in one paragraph → The normal cycle → What the user sees → What can go wrong → How we'll know it's working → Lifecycle diagram → TL;DR. Length target: 400-700 lines for complex designs.
  7. 97 / 98. Filled when the doc index includes them. 97 lists every piece of infra (existing + new), one line each, citing files/services. 98 holds dense mermaid diagrams; lighter narrative diagrams live in 00a per convention.
  8. Resolve cross-references. After every doc in the artifact exists, call skills/_shared/storage-resolution.md (resolve_links) once over the artifact to turn [[…]] wikilinks into Notion page mentions. Backend-neutral: a no-op on the filesystem backend, the mention second pass on notion (see skills/_shared/notion-translation.md).
  9. Self-review pass (see below). Read the written docs back via skills/_shared/storage-resolution.md (read_artifact) and run a final pass over the whole artifact.
  10. Flip status to in-review per skills/_shared/storage-resolution.md (set_status), which also bumps updated:. Print: "Design ready for review. Walk through it and tell me when to mark it approved."
  11. Status approved. User-driven only. User says "approved" → flip status per skills/_shared/storage-resolution.md (set_status); when the design has a 95-visual-contract slot, rewrite its freeze record from frozen: none to frozen: NN (the latest version) via write_doc in the same moment: an approved design with a 95 slot always names a frozen version, the invariant /c-plan relies on. Post-approval mockup changes are design drift under the existing drift rules, never a silent new version. Then print: "Run /c-plan to write the implementation plan."

Read the full file on GitHub · 119 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. 6d ago First seen · 119 lines · 0 tokens per session scan A c66079a85530

Subscribe to this mod's changes

c-design is a skill published in the GitHub repository sentasity/cadence (1 stars, last pushed 11d ago), licensed MIT. It adds 109 tokens to every session and 3,756 once invoked, about $0.0005 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 skills, from other repositories

fidelity-gate

Build a UI against a frozen visual reference without drift - an inventory extracted before any code, a relics list, and a gate that MEASURES computed styles on a fixture carrying the reference's own data. Use when a mockup, design spec or screenshot is the contract.

jjanczur/tyran · 56 tokens

figma-fetch

Extract frame/component structure and all visible text from a Figma design URL. Use whenever a prompt or a fetched issue contains a figma.com/design or figma.com/file link.

theam/claude-dev-kit · 40 tokens

design

Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…

cryndoc/polisade-orchestrator · 162 tokens

self-improve

Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.

SpaiR/task-pipeline · 76 tokens

self-audit

Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.

SpaiR/task-pipeline · 52 tokens

designer

Settle the look before the pixels — audience and context first, then the base and the delta, taste settled by looking at real states, accessibility as the floor, one design language committed to DESIGN.md as tokens with roles. A command the user types, for work with an interface someone will see; standalone, no other…

donald-ada/workinggenius · 69 tokens