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 jamesgray-ai/handsonai-plugins --skill analyzegit 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/analyze)<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/analyze"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/analyze/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/jamesgray-ai/handsonai-plugins/analyze"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/analyze.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 | $0.00154 | $0.09973 |
| Opus 5.5 | $0.00062 | $0.03989 |
| Sonnet 5.5 | $0.00031 | $0.01995 |
| Haiku 4.5 | $0.00015 | $0.00997 |
Grade A, and why
analyze 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 4d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Workflows
Your first text is a line for the leader. Every word of text you write reaches the leader as a chat message, text before or between tool calls included. So the first text you write in a chat is your first line to the leader (the opening, a routing line, a resume line or an entry check's question): until then, make tool calls with no text at all, not even a few words on what you're reading, the state you found or what comes next. After it, write text only when it's for the leader, and never narrate your own work (files read, scripts run, states, the rule you're applying).
This skill records each opportunity the student has to get more value from AI (friction to remove, or work they'd do more of, or better, with the time) as a candidate workflow: the work, the pain, its size and the value lever. It catalogs: it names each workflow and describes it well. It never ranks the workflows or picks one to build first; Deconstruct opens with that choice. It ends with a backlog and an opportunity report.
Workflow
Entry, before the opening
Follow references/routing.md's "The order at every entry", before anything is read, saved or said, using the framework-state script where code can run (the plugin's copy, as the other steps use, never the workspace's tools/ copy, which can be out of date: node [plugin root]/tools/framework-state.js <workflow folder>, or with --continue <framework folder> for "continue my workflow"; the plugin root is two folders above this skill's folder; on a non-zero exit, or where code can't run, apply routing.md by hand). Never mention the script. Analyze skips the wrong-place check: it writes nothing a workflow reads at runtime. Started by name, Analyze is always the owner.
Platform registry: platform facts (how a folder is selected on Claude desktop: the
claudeentry'scapabilities.desktop_add_folder; which drives a connection can write to) come fromregistries/platform-registry.jsonat the plugin root, or elsehttps://raw.githubusercontent.com/jamesgray-ai/handsonai/main/plugins/handsonai/registries/platform-registry.json, read once per session.
What ships with it
7 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.
- 4d ago Changed · -31 lines · +41 tokens per session 1a56100118bf
- 26d ago Changed 3799426c3bbf
- 1mo ago Changed · -25 lines 764783006115
- 1mo ago Changed · +28 lines · +22 tokens per session 506691b31cc5
- 1mo ago Changed · +2 lines cc6422187689
- 1mo ago Changed 409606832037
- 1mo ago Changed · +31 lines · +14 tokens per session be65bc9d4fcc
- 2mo ago First seen · 235 lines · 77 tokens per session scan A e3a73b08edbf
analyze is a skill published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 154 tokens to every session and 9,973 once invoked, about $0.0006 per session on Opus 5.5. 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.
analyze compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| analyzejamesgray-ai/handsonai-plugins | Skill | 8 | yesterday | MIT | A | 154 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |