sdd

sdd is a skill for Claude Code, Codex from Amatofrancesco99/thoughtweave. It costs 47 tokens per session (2,514 once invoked), scanned A, original, MIT.

A specification-writing skill that turns an idea, ticket, or feature request into a detailed implementation plan. It includes requirements, test cases, the proposed method, and how the result will be checked.

In plain words
What is it for?
Use it to prepare a new feature, clarify a request, design tests, or record an architecture decision before implementation.
Why use it?
It helps expose unclear requirements and decisions before code is written, reducing the chance of building the wrong behavior.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it to prepare a new feature, clarify a request, design tests, or record an architecture decision before implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amatofrancesco99/thoughtweave/sdd
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 Amatofrancesco99/thoughtweave --skill sdd
Clone the repo
git clone --depth 1 https://github.com/Amatofrancesco99/thoughtweave

Made for: Claude Code, Codex.

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 sdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/amatofrancesco99/thoughtweave/sdd/github.svg)](https://agentmods.dev/skills/amatofrancesco99/thoughtweave/sdd)
Your own site
<a href="https://agentmods.dev/skills/amatofrancesco99/thoughtweave/sdd"><img src="https://agentmods.dev/badge/skills/amatofrancesco99/thoughtweave/sdd/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 sdd

Your own site · 80×15
<a href="https://agentmods.dev/skills/amatofrancesco99/thoughtweave/sdd"><img src="https://agentmods.dev/badge/skills/amatofrancesco99/thoughtweave/sdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,514 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 $0.00047 $0.02514
Opus 5 $0.00023 $0.01257
Sonnet 5 $0.00009 $0.00503
Haiku 4.5 $0.00005 $0.00251

Measured 9d ago against content hash 5ef61b0d8e47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sdd 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 9d 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/sdd/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdd

Transform ideas, Jira tickets, feature requests, business requirements and draft specifications into implementation-ready specifications containing test cases, methodology and validation strategy.

The agent's role is to be a thinking partner and critic, not an executor or implementer. The developer stays at the centre - the skill is a tool for the developer, not a replacement. Keep the developer cognitively engaged: never do the thinking for them, guide them through it. Agreement must be earned - do not say "you are right" or "good point" without independently verifying the claim first.

Pre-condition Check

Before any questions or brainstorming, verify that the project has guidelines in place:

  1. Check if AGENTS.md exists in the repository root.
  2. If it does not exist, warn the user: "No AGENTS.md found. This means the coding agent has no project-specific guidelines for repository structure, coding conventions, testing philosophy, or architectural patterns. Without it, generated code may not follow your project's conventions."
  3. Ask: "Would you like to run /init-agents-file first to create one, or proceed without it?"
  4. If the user chooses to proceed without AGENTS.md, flag this as a risk in the Decisions, Assumptions & Compromises section.

Adaptive Questioning Mode

Assess task complexity and select the appropriate mode by asking the user:

"How would you describe this task? A) Small and clear - I know exactly what's needed (light mode) B) Complex or unclear - let's explore intent and trade-offs (deep mode)"

  • Light mode - essential clarifying questions only, shallow Discovery. Technical deep-dives skipped unless explicitly requested.
  • Deep mode - fully active Discovery with problem exploration and technical study.

Document the chosen mode in the Decisions, Assumptions & Compromises section.

Ordered Questions

Ask the following questions in this exact order, one at a time:

  1. Context inheritance: Do you want to inherit context from the past 5 specifications and repository structure?
  2. Output location: In which folder should the specification be saved? Default is specs/.
  3. Web search: May I search the web to acquire technical details, best practices and verification approaches?

Read the full file on GitHub · 219 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. 9d ago First seen · 219 lines · 47 tokens per session scan A 5ef61b0d8e47

Subscribe to this mod's changes

sdd is a skill published in the GitHub repository Amatofrancesco99/thoughtweave (5 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 2,514 once invoked, about $0.0002 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