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 bezael/sdd-creator --skill dominicode-sdd-creatorgit clone --depth 1 https://github.com/bezael/sdd-creatorWrote 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/bezael/sdd-creator/dominicode-sdd-creator)<a href="https://agentmods.dev/skills/bezael/sdd-creator/dominicode-sdd-creator"><img src="https://agentmods.dev/badge/skills/bezael/sdd-creator/dominicode-sdd-creator/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/bezael/sdd-creator/dominicode-sdd-creator"><img src="https://agentmods.dev/badge/skills/bezael/sdd-creator/dominicode-sdd-creator.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 | $0.00101 | $0.05855 |
| Opus 5 | $0.00051 | $0.02927 |
| Sonnet 5 | $0.00020 | $0.01171 |
| Haiku 4.5 | $0.00010 | $0.00585 |
Grade B, and why
dominicode-sdd-creator scanned grade B with 1 finding 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 12d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- **State the cost once, in one sentence, without moralizing:** no regression detection, no confident refactoring, and every acceptance criterion gets verified by hand instead of by a runner. How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dominicode SDD Creator
This skill turns a vague product idea or issue into a complete, evidence-driven SDD lifecycle. Code still starts only after Spec → Plan → Tasks, and completion requires verification, review and a final regression gate.
SDD adaptation by Bezael Pérez · Dominicode.
The methodology in one sentence
Understand → Spec → Plan → Tasks → Implement → Verify (Fix → Verify on failure) → Code Review → Final Verify → PR / Handoff.
spec.md, plan.md and tasks.md are the durable sources of truth. Evidence, review and final verification prove those decisions were satisfied; .work/implementation.md remains disposable execution scratch.
When to use this skill
Trigger this skill at the start of any non-trivial coding work, even if the user did not say the word "spec". Signals:
- Phrases like "I want to build...", "let's create...", "spec this out", "plan this feature", "design X", "scaffold a new project", "start a new MVP"
- A feature description without prior planning artifacts in the conversation
- A coding request that touches more than one module, layer, or screen
- A request that would normally generate >100 lines of code
Do not trigger for:
- Bug fixes with a clear repro
- Small refactors with a single file in scope
- Pure questions ("how does X work?")
- Continuing work on a feature where a
specs/<name>/spec.mdalready exists (read it instead)
Workflow (hybrid mode)
Step 0 — Detect the context level
Look at the conversation so far and classify what the user has given you:
| Level | Signal | Action |
|---|---|---|
| HIGH | Detailed PRD, ticket, doc, or 3+ paragraphs of context | Produce a full draft of the 6 sections + list "Open questions" at the end |
| MEDIUM | 1–2 sentences with clear goal but missing detail | Produce a draft, mark unknowns with [NEEDS CONFIRMATION: ...] inline |
| LOW | Vague request ("quiero hacer una app de X") | Interview the user one section at a time — do NOT dump all 6 questions at once |
What ships with it
15 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.
- AGENTS.md 21 KB
- references/code-review.md 5.6 KB
- references/codebase-inspection.md 5.4 KB
- references/examples.md 8.4 KB
- references/final-verification.md 3.3 KB
- references/tdd-workflow.md 6.5 KB
- references/test-runner-detection.md 10 KB
- references/traceability.md 5.6 KB
- references/verification-loop.md 4.9 KB
- templates/implementation.md 3.2 KB
- templates/plan.md 4.0 KB
- templates/spec.md 5.1 KB
- templates/specs-index.md 2.3 KB
- templates/tasks-no-tdd.md 11 KB
- templates/tasks.md 10 KB
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.
- 12d ago First seen · 278 lines · 101 tokens per session scan B fba7d75370bf
dominicode-sdd-creator is a skill published in the GitHub repository bezael/sdd-creator (15 stars, last pushed 12d ago), licensed MIT. It adds 101 tokens to every session and 5,855 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…