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 ahgraber/skills --skill sdd-derivegit clone --depth 1 https://github.com/ahgraber/skillsWrote 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/ahgraber/skills/sdd-derive)<a href="https://agentmods.dev/skills/ahgraber/skills/sdd-derive"><img src="https://agentmods.dev/badge/skills/ahgraber/skills/sdd-derive/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/ahgraber/skills/sdd-derive"><img src="https://agentmods.dev/badge/skills/ahgraber/skills/sdd-derive.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 | $0.00054 | $0.04079 |
| Opus 5 | $0.00027 | $0.02039 |
| Sonnet 5 | $0.00011 | $0.00816 |
| Haiku 4.5 | $0.00005 | $0.00408 |
Grade A, and why
sdd-derive 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD Derive
Orchestrate spec generation from existing code: a change directory (new or modified behavior) or baseline specs (retroactive documentation).
The orchestrator holds context across phases; subagents are dispatched for scoped work that benefits from context isolation.
SPECS_ROOTis resolved by thesddrouter before this skill runs. Replace.specs/with the project's actual specs root.
Writing Style
Write the derived specs in the voice of a professional technical writer. Prefer ASD-STE100 Simplified Technical English: short sentences, one instruction per sentence, active voice, and one term per concept. Keep identifiers, commands, paths, and RFC 2119 keywords exact.
When to Use
- Deriving specs from existing code ("derive SDD specs for the auth flow")
- Documenting implemented behavior retroactively into baseline specs
- Producing a change directory for behavior already implemented
- User phrases: "derive specs", "generate specs from code", "retrofit specs", "document this code in SDD"
When Not to Use
- Translating specs from another tool or format — use
sdd-translate - No codebase and no existing behavior to anchor against — use
sdd-propose - Exploring a problem before deciding what to spec — use
sdd-explore
Invocation Notice
- Tell the user when this skill is running:
sdd-derive. Skip the notice when the user asked for the skill by name or slash command; spelling and spacing need not match. A phrase from this skill's own trigger list is not a name — naming the work is not naming the skill.
Determine Output Type
Baseline specs (.specs/specs/) document implemented behavior.
Write baseline specs only when existing code anchors them; otherwise generate a change directory.
digraph output_type {
".specs/specs/ exists?" [shape=diamond];
"Codebase has relevant\nimplementation?\n(answered by Phase 2 discovery)" [shape=diamond];
"New or existing behavior?" [shape=diamond];
"Generate change directory\n(.specs/changes/<name>/)\nADDED-only delta specs" [shape=box];
"Generate change directory\n(.specs/changes/<name>/)" [shape=box];
"Generate baseline specs\n(.specs/specs/)" [shape=box];
".specs/specs/ exists?" -> "Codebase has relevant\nimplementation?\n(answered by Phase 2 discovery)" [label="no"];
"Codebase has relevant\nimplementation?\n(answered by Phase 2 discovery)" -> "Generate baseline specs\n(.specs/specs/)" [label="yes — retroactive doc"];
"Codebase has relevant\nimplementation?\n(answered by Phase 2 discovery)" -> "Generate change directory\n(.specs/changes/<name>/)\nADDED-only delta specs" [label="no — greenfield"];
".specs/specs/ exists?" -> "New or existing behavior?" [label="yes"];
"New or existing behavior?" -> "Generate change directory\n(.specs/changes/<name>/)" [label="new or modified"];
"New or existing behavior?" -> "Generate baseline specs\n(.specs/specs/)" [label="retroactive doc"];
}
What ships with it
18 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.
- assets/sdd-derive-output-type.svg 7.4 KB
- assets/sdd-derive-phase-2-discovery.svg 13 KB
- assets/sdd-derive-phase-4-per-capability.svg 8.5 KB
- assets/sdd-derive-subagent-dispatch.svg 8.6 KB
- references/derive-spec-additions.md 3.5 KB
- references/discovery.md 15 KB
- references/evidence-class-taxonomy.md 8.7 KB
- references/lifter.md 12 KB
- references/observer.md 7.1 KB
- references/sdd-change-formats.md 42 B
- references/sdd-derive-output-type.dot 1.4 KB
- references/sdd-derive-phase-2-discovery.dot 1.8 KB
- references/sdd-derive-phase-4-per-capability.dot 1.4 KB
- references/sdd-derive-subagent-dispatch.dot 1.3 KB
- references/sdd-schema.md 34 B
- references/sdd-spec-formats.md 40 B
- references/validate.md 5.8 KB
- references/validate.py 17 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.
- 9d ago First seen · 352 lines · 54 tokens per session scan A a5cd0e599cb7
sdd-derive is a skill published in the GitHub repository ahgraber/skills (5 stars, last pushed 2d ago), licensed CC0-1.0. It adds 54 tokens to every session and 4,079 once invoked, about $0.0003 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…