openspec-design

openspec-design is a skill for Claude Code from digital-stoic-org/agent-skills. It costs 66 tokens per session (993 once invoked), scanned A, original, MIT.

A design-planning tool for OpenSpec changes, a structured way to describe software work before implementation. It checks whether the proposal belongs to one bounded area and produces a design document when it does.

In plain words
What is it for?
Use it to create a design document, check whether work should be split, and describe architecture, data relationships, or workflows.
Why use it?
It helps turn a broad proposal into a focused design with clear structure, dependencies, and process flows before tasks are created.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter.

Part of the openspec plugin — 9 skills shipped together

Good fit Use it to create a design document, check whether work should be split, and describe architecture, data relationships, or workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/digital-stoic-org/agent-skills/openspec-design
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.

Any agent
npx skills add digital-stoic-org/agent-skills --skill openspec-design
Clone the repo
git clone --depth 1 https://github.com/digital-stoic-org/agent-skills

Made for: Claude Code.

Or install openspec, the plugin that ships this one along with the rest of its 9 skills.

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 openspec-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/openspec-design/github.svg)](https://agentmods.dev/skills/digital-stoic-org/agent-skills/openspec-design)
Your own site
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/openspec-design"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/openspec-design/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 openspec-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/openspec-design"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/openspec-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 993 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 4
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • low Excessive Agency · line 14
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
How audits are shown
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 $0.00066 $0.00993
Opus 5.5 $0.00026 $0.00397
Sonnet 5.5 $0.00013 $0.00199
Haiku 4.5 $0.00007 $0.00099

Measured 1mo ago against content hash d922b3995172, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openspec-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 1mo 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.

openspec/skills/openspec-design/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSpec Design

BC-first structural design engine. Produces design.md — the missing layer between proposal.md and tasks.md.

Domain-agnostic: Containers are any bounded unit — services, files, skill directories, workflow phases, document sections, process stages. Not limited to software architecture. Choose the zoom level that fits the change.

You are designing: $ARGUMENTS

Commands

design

Analyze proposal → BC check → Minimal Design Kit → write design.md.

Input: $ARGUMENTS = design <change-id>

Workflow:

  1. Read context:

    • openspec/project.md → execution mode
    • openspec/changes/{id}/proposal.md → change scope
  2. BC check (mandatory first step — stop if fails):

    • Scan proposal for BC violation signals (see reference.md §BC Signals)
    • If multi-domain detected → output split recommendation and STOP
    • If single-domain → proceed
  3. Design phase (only if BC check passes):

    • Produce all 5 sections of design.md (see §Output Format)
    • Maintain mode (project.md mode = maintain) → delta-only, skip full kit
  4. Write: openspec/changes/{id}/design.md

BC split output (stop before design artifacts):

⚠️ Bounded Context boundary crossed

This change appears to span multiple domains:
- BC1: {name} — {what it owns}
- BC2: {name} — {what it owns}

Recommendation: Split into separate OpenSpec changes:
1. openspec-plan create {change-id}-{bc1}: {description}
2. openspec-plan create {change-id}-{bc2}: {description}

Why: 1 change = 1 BC enables isolated testing, clear ownership,
and tractable troubleshooting. Mixing domains creates ambiguous
failures where you can't tell which boundary is broken.

Override: Add ADR to proposal.md documenting why mixed-domain is
intentional, then re-invoke /openspec-design design {id}.

maintain

Delta-only design update for an existing design.md.

Input: $ARGUMENTS = maintain <change-id>

Workflow:

  1. Read existing openspec/changes/{id}/design.md
  2. Read proposal.md for what changed
  3. BC check on the delta only
  4. Output: which sections change, what moves, why
  5. Append ## Delta section to design.md (do not rewrite existing sections)

Read the full file on GitHub · 108 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 108 lines · 66 tokens per session scan A d922b3995172

Subscribe to this mod's changes

openspec-design is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 12d ago), licensed MIT. It adds 66 tokens to every session and 993 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-04.

Related

Other skills, from other repositories