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 Amatofrancesco99/thoughtweave --skill sddgit clone --depth 1 https://github.com/Amatofrancesco99/thoughtweaveWrote 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/amatofrancesco99/thoughtweave/sdd)<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.
<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>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 | $0.00047 | $0.02514 |
| Opus 5 | $0.00023 | $0.01257 |
| Sonnet 5 | $0.00009 | $0.00503 |
| Haiku 4.5 | $0.00005 | $0.00251 |
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.
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:
- Check if
AGENTS.mdexists in the repository root. - 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."
- Ask: "Would you like to run /init-agents-file first to create one, or proceed without it?"
- 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:
- Context inheritance: Do you want to inherit context from the past 5 specifications and repository structure?
- Output location: In which folder should the specification be saved? Default is
specs/. - Web search: May I search the web to acquire technical details, best practices and verification approaches?
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.
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.
- 9d ago First seen · 219 lines · 47 tokens per session scan A 5ef61b0d8e47
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.
Other skills, from other repositories
harness
Route Harness Starter Kit workflows. Use when the user invokes /harness with adopt, doctor, update, refresh, review, or review sub-agent, or asks to apply, diagnose, maintain, or review repository harness guidance.
harness-adopt
Apply Harness Starter Kit prompt-first adoption to a target repository. Use when the user asks to apply, install, adopt, or bootstrap repository harness guidance, checks, memory, and adoption reporting.
harness-review
Review the current change set from an opposing harness-engineering perspective. Use when the user asks for /harness review, /harness review sub-agent, or a no-edit harness review.
harness-update
Refresh an adopted target repository from the latest Harness Starter Kit reference. Use when the user asks for /harness update or wants source tracking and selective harness updates.
harness-doctor
Run the diagnostic Harness Doctor workflow. Use when the user asks for /harness doctor, harness score, repository harness readiness, or a no-edit harness health report.
harness-refresh
Review stale, duplicated, obsolete, or unused target harness guidance. Use when the user asks for /harness refresh or wants harness maintenance recommendations without default edits.