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 rhythmic-tastegit 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/rhythmic-taste)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/rhythmic-taste"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/rhythmic-taste/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/rhythmic-taste"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/rhythmic-taste.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 | $0.01145 |
| Opus 5 | $0.00031 | $0.00573 |
| Sonnet 5 | $0.00012 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
rhythmic-taste 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rhythmic taste
Vary structural rhythm and variation across a document's sections. The core is rhythm: the pattern of length, density, pacing, and nesting that keeps a reader moving, and the deliberate variation that keeps them awake. A document whose sections all read the same — same length, same shape, same cadence — flattens attention regardless of how good each section is.
Two modes: document mode (default) derives a rhythm constraint from the document's own sections, no external inputs required; and seeded constraint mode (optional) adds random variation from a disclosed seed and the user's chosen random inputs.
Contract
| Field | Bound contract |
|---|---|
| Trigger | User says "give this rhythm", "vary the structure", "the sections all read the same", or asks for section or layer rhythm variation. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Chat output only. A rhythm constraint for sections or layers, not used as factual authority. |
| Done | A rhythm constraint is derived and presented: in document mode, from the document's own sections; in seeded constraint mode, additionally from the disclosed seed and the user's chosen random inputs. |
Inputs
- The document or section list (required in document mode): the sections, layers, or structural units to vary, supplied directly or read from the artifact in scope.
- Random seed (optional, required only for seeded constraint mode): a number, word, or phrase the user discloses openly.
- Random inputs (optional, required only for seeded constraint mode): titles, words, or items the user supplies or fetches from a random source. Any count the user chooses; no fixed minimum.
Procedure — document mode (default)
- Receive the document or section list. If sections are not supplied, derive them from the artifact's headings, layers, or structural breaks.
- Measure each section's structural properties: relative length, sentence or paragraph density, pacing (tight to expansive), and nesting depth.
- Diagnose the current rhythm: name the pattern the sections follow (steady pulse, monotone, crescendo, decrescendo, syncopated) and where variation is missing — which sections collapse to the same shape.
- Choose a target rhythm pattern from: alternating long-short, crescendo (short to long), decrescendo (long to short), syncopated (irregular gaps), or steady pulse. Choose the pattern that serves the document's purpose, not the one closest to the current shape.
- Map the target pattern to section assignments: set relative length or density per section, set pacing from the chosen pattern, and assign nesting where the content calls for sub-sections. Vary the assignments so no two adjacent sections collapse to identical structure.
- Present the derived rhythm constraint as a structured list of section assignments with pacing, density, and nesting instructions, preceded by the diagnosed current rhythm and the chosen target pattern.
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 · 58 lines · 62 tokens per session scan A e3593f4616d0
rhythmic-taste 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 1,145 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…