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 magnus919/hermes-profiles --skill sdd-work-decompositiongit clone --depth 1 https://github.com/magnus919/hermes-profilesWrote 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/magnus919/hermes-profiles/sdd-work-decomposition)<a href="https://agentmods.dev/skills/magnus919/hermes-profiles/sdd-work-decomposition"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-profiles/sdd-work-decomposition/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/magnus919/hermes-profiles/sdd-work-decomposition"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-profiles/sdd-work-decomposition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.01151 |
| Opus 5 | $0.00031 | $0.00575 |
| Sonnet 5 | $0.00012 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
sdd-work-decomposition 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD Work Decomposition
Translating a reviewed, approved specification into an executable sequence of tasks with explicit dependencies, per-task acceptance criteria, and integration directives for the implementation agent.
SDD Pipeline Position
SPECIFY → [PLAN] → TASKS → IMPLEMENT → VERIFY
↑
You are here
This skill bridges the gap between what to build (the spec) and how to build it in independent, verifiable units. It produces both the human-readable task plan and the CLAUDE.md / AGENTS.md content that drives the implementation agent.
Core Principle: Spec Is the Plan
This skill does not invent a plan from scratch. It extracts the plan from the specification. The spec already defines the behavior the system must exhibit — each behavior maps to a task. Every task traces to a specific section of SPEC.md. There is no work in the plan that is not required by the spec, and no requirement in the spec that is not addressed by at least one task.
This is what distinguishes SDD decomposition from general-purpose project planning. The planner does not ask "what work needs to happen?" — the spec already answered that. The planner asks "how do we sequence and package this work for safe execution?"
Artifact-Pyramid Output: TASK-PLAN.md
The task plan follows the artifact-pyramid structure:
| Layer | Content | File |
|---|---|---|
| L1 | Phase overview — total task count, critical path estimate, key dependencies, recommended execution order | 00-index.md (entry point) |
| L2 | Task groups by phase or feature area — dependency graph, per-group acceptance criteria derived from spec sections | Individual *.phase.md files |
| L3 | Individual task cards — each with spec-derived ACs, estimated complexity, preconditions, CLAUDE.md directives | tasks/ directory |
| SOURCES | Cross-reference from each task to the SPEC.md section it implements | Footer of each file |
Loading Guidance
| Reference | When to load | File |
|---|---|---|
| Task Decomposition Methodology | Before writing any task plan — patterns for spec-to-task extraction, sizing, atomicity | references/task-decomposition-methodology.md |
| Dependency Mapping | Sequencing tasks with real constraints — spec-derived dependency chains, not guesswork | references/dependency-mapping.md |
| CLAUDE.md as Spec Layer | After producing the task plan — generating CLAUDE.md directives for the implementation agent | references/claude-dot-md-as-spec-layer.md |
What ships with it
5 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.
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 · 88 lines · 62 tokens per session scan A d42803e88a52
sdd-work-decomposition is a skill published in the GitHub repository magnus919/hermes-profiles (161 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 1,151 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 2026-08-30.
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…
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…