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 agentmods add skills/jamesgray-ai/handsonai-plugins/deconstructnpx skills add jamesgray-ai/handsonai-plugins --skill deconstructgit clone --depth 1 https://github.com/jamesgray-ai/handsonai-pluginsWrote 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/jamesgray-ai/handsonai-plugins/deconstruct)<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/deconstruct"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/deconstruct.svg" alt="Measured on agentmods" 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 | $0.00171 | $0.11662 |
| Opus 5 | $0.00086 | $0.05831 |
| Sonnet 5 | $0.00034 | $0.02332 |
| Haiku 4.5 | $0.00017 | $0.01166 |
Grade A, and why
deconstruct 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 3d 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 — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Deconstruction
Step 2 is the PRD for the workflow. It captures what the workflow must do and the rules it must follow — not how AI building blocks will deliver it (that's Step 3, Design).
The output is a Workflow Requirements document written in clear, concise requirements language. It must be self-contained enough that a reader who never saw this conversation — including the Design skill or any agent model — can act on it without re-interviewing the user.
The Two Paths
Step 2 has two paths, mapped directly to the two ways students think about a workflow:
| Path | When to use | Mental model |
|---|---|---|
| Step-driven (a known-steps workflow) | The work runs the same way each run — you can describe how it gets done, even if the steps aren't mapped yet. Design will classify it as a deterministic or guided workflow — both run on steps you own. | "I know how the work gets done" |
| Goal-driven (an agent system) | You know what "done" looks like, but the work takes different steps depending on what comes in — so you give an agent system a goal and let it figure out the steps at runtime. Design classifies these as autonomous. | "I know the goal" |
Both paths produce a Workflow Requirements document with the same shared shell — only the middle "what does the workflow do" block differs.
What "goal" means here. An agent goal is a deliverable with a completion state — something you can look at after a single run and verify is done. It is not a business objective or an impact metric: "higher revenue" is a business objective (record it in Value & Measurement → Business Objective); "a ranked list of 20 qualified prospects matching our ICP, with contact info" is an agent goal. The goal bundles the deliverable plus the rules and acceptance criteria for it — what major agent frameworks call the expected output and success criteria. (If you know the product-management "outcomes over outputs" framing: the agent's goal is closer to an output — the business outcome belongs in Business Objective.) The defining trait of this path is who owns the control flow: the agent decides the path to the goal at runtime, while you own the definition of done. Note the inverse doesn't hold — a step-driven workflow can still use an agent for an individual step; what makes a workflow goal-driven is that the agent decides the overall sequence, not merely that agents are involved.
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.
- 3d ago First seen · 497 lines · 171 tokens per session scan A 3bcf1ea10c59
deconstruct is a skill published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed 22d ago), licensed MIT. It adds 171 tokens to every session and 11,662 once invoked, about $0.0009 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…