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 skills add d-mariano/spicyclaude --skill design-breakdowngit clone --depth 1 https://github.com/d-mariano/spicyclaudeWrote 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.
[](https://agentmods.dev/skills/d-mariano/spicyclaude/design-breakdown)<a href="https://agentmods.dev/skills/d-mariano/spicyclaude/design-breakdown"><img src="https://agentmods.dev/badge/skills/d-mariano/spicyclaude/design-breakdown/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.
<a href="https://agentmods.dev/skills/d-mariano/spicyclaude/design-breakdown"><img src="https://agentmods.dev/badge/skills/d-mariano/spicyclaude/design-breakdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00157 | $0.04686 |
| Opus 5 | $0.00078 | $0.02343 |
| Sonnet 5 | $0.00031 | $0.00937 |
| Haiku 4.5 | $0.00016 | $0.00469 |
Grade A, and why
breaking-down-design-docs 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 11d 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breaking down design docs
The default failure mode of this task is producing a tidy-looking list of tickets that hides ambiguity. Resist that. It is better to surface three real questions than to invent answers and ship a clean-looking breakdown built on guesses.
Early exit: if the doc is a problem statement without a proposed solution, don't fake a breakdown. Say so and offer to break the discovery work down into spikes instead.
The workflow has a hard gate
Three phases. Do not skip from Phase 2 to Phase 3 without explicit user confirmation. That gate is the whole point of this skill — it gives the user a chance to redirect the breakdown before you've spent effort expanding stories that will be thrown away.
Copy this checklist into your response and check items off as you go:
Breakdown progress:
- [ ] Phase 1: Read doc, ground in repo context, surface clarifying questions
- [ ] Phase 1 GATE: User has answered the must-answer questions (or said "skip, your call")
- [ ] Phase 2: Propose epic structure + story titles (one line each) + pushback
- [ ] Phase 2 GATE: User has confirmed or revised the split
- [ ] Phase 3: Expand each confirmed story to full markdown
- [ ] Phase 3: (Optional) Push to Jira if `acli` is available and user opted in
Phase 1: Read and ground
If the user has only mentioned a design doc without sharing it, ask for the path, URL, or pasted content before proceeding. Otherwise, read the doc carefully. Then, before drafting anything:
Ground the breakdown in repo reality (Claude Code only). A breakdown disconnected from the codebase is fiction. Spend a few tool calls doing things like:
- Look at the repo's top-level structure and
README.mdto understand what's already there. - Search for any module, service, or file the design names. If the design says "extend the
BillingService", confirmBillingServiceactually exists and skim it. - Check existing tests near the touched code — they reveal real contracts and edge cases the doc may omit.
- If the design references an external API or library, check whether it's already a dependency.
What ships with it
9 files 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.
- evals/01-happy-path.json 2.6 KB
- evals/02-problem-statement.json 1.3 KB
- evals/03-ambiguous-doc.json 2.0 KB
- evals/README.md 1.6 KB
- fixtures/notifications-ambiguous.md 1.9 KB
- fixtures/onboarding-problem-statement.md 1.4 KB
- fixtures/payments-idempotency.md 2.3 KB
- references/jira-integration.md 5.5 KB
- references/publish-breakdown-acli.sh 8.4 KB runs code
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.
- 11d ago First seen · 301 lines · 157 tokens per session scan A f31e8aa1854f
breaking-down-design-docs is a skill published in the GitHub repository d-mariano/spicyclaude (5 stars, last pushed 1mo ago), licensed MIT. It adds 157 tokens to every session and 4,686 once invoked, about $0.0008 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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.