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 OutlineDriven/odin-claude-plugin --skill scaffold-exercisesgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/scaffold-exercises)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/scaffold-exercises"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/scaffold-exercises/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/outlinedriven/odin-claude-plugin/scaffold-exercises"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/scaffold-exercises.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 | $0.00921 |
| Opus 5 | $0.00031 | $0.00461 |
| Sonnet 5 | $0.00012 | $0.00184 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
scaffold-exercises 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 5d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold exercises
Contract
| Field | Bound contract |
|---|---|
| Trigger | A course needs numbered problem, solution, and explainer scaffolds. |
| Authority | Write only to tracked section and exercise files/directories in the working directory. Revert with standard VCS. |
| Side effect | Creates or updates numbered section and exercise files and directories. |
| Done | A JSON object naming scaffolded paths and linter status, with no unvalidated scaffold left on disk. |
Inputs
Must be supplied:
section— the section number as a non-negative integer (e.g. 1, 2, 3)exercise— the exercise number as a positive integertype— one of:problem,solution,explainerbase_path— the directory under which sections and exercises live (must be a tracked VCS path)
Procedure
-
Validate inputs and
base_path. Confirmsectionis a non-negative integer,exerciseis a positive integer,typeis one of the three allowed values, andbase_pathis a non-empty string pointing to a directory that exists and is tracked by the local VCS. Stop on any validation failure without writing. Done when: all inputs pass validation. -
Compute the section subdirectory and a type-specific exercise filename. The section subdirectory is
base_path/section-Nwhere N is the section number left-padded to two digits. The exercise filename isexercise-M-<type>.mdwhere M is the exercise number left-padded to two digits and<type>is the supplied type value. The three types produce distinct filenames (exercise-M-problem.md,exercise-M-solution.md,exercise-M-explainer.md) so they do not collide or overwrite each other. Done when: the subdirectory and filename are computed. -
Create the directory chain and file. Create the section subdirectory if it does not exist. Create the exercise file at the computed path. Done when: the directory chain and file exist.
-
Populate the scaffold with the type-specific heading. For
problem: emit## Exercise N.Nwhere N.N is section.exercise, then a blank line, then a fenced code block with the language unspecified. Forsolution: emit## Exercise N.N Solution, then a blank line. Forexplainer: emit## Exercise N.N Explained, then a blank line. Write the populated content to the file. If the write fails, stop and report the failure. Done when: the file contains the type-specific heading and scaffold.
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.
- 5d ago First seen · 49 lines · 62 tokens per session scan A 3a04efd33617
scaffold-exercises is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 62 tokens to every session and 921 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 2026-09-04.
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…