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 minimalism-drivengit 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/minimalism-driven)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/minimalism-driven"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/minimalism-driven.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00858 |
| Opus 5 | $0.00022 | $0.00429 |
| Sonnet 5 | $0.00009 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
minimalism-driven 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 yesterday.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Minimalism driven
Contract
| Field | Bound contract |
|---|---|
| Trigger | Writing or restructuring code; considering a helper, wrapper, config key, or dependency; or an explicit request for minimal code, DRY code, or no gold-plating. |
| Authority | Reversible local: writes only reversible local edits needed by the ask; rollback is version control or undo. No remote mutation. |
| Side effect | Edit code within the requested scope; do not implement adjacent improvements. |
| Done | Every addition has a concrete reason, intent and failure behavior are obvious, and the resulting scope exactly matches the ask. |
Inputs
Supply the requested behavior and the local code surface to change. Supply explicit constraints or acceptance criteria when they exist. Existing nearby implementations and call sites are required evidence for reuse decisions; no additional input is optional if its absence would require guessing behavior.
Procedure
- Bound the requested behavior, affected files, and acceptance criteria before editing. If any required behavior cannot be determined from the request or local code, stop rather than invent it. Done when: the behavior, files, and criteria are stated and no unknown remains.
- Inspect the affected code and its relevant call sites for an existing implementation or convention that can satisfy the ask; reuse that before creating a second form. Done when: every reuse candidate is identified and the reuse-or-create decision is recorded.
- Try deletion first, then modification of existing code. Add new code only when neither can produce the required behavior. Done when: the smallest-form approach is selected and justified.
- Before adding a helper, wrapper, config key, dependency, branch, or other surface, state its concrete necessity in one sentence. Omit it if removing it would leave the requested outcome unchanged. Done when: every retained addition has a stated necessity and every rejected addition is omitted.
- Keep each retained addition sufficient rather than merely short: use clear names, handle required error paths, and encode or state assumptions where the code otherwise permits a silent gap. Done when: every addition handles its required error paths and states its assumptions.
- Make only the bounded local edits. Do not build an adjacent improvement; report it separately only when it materially affects the requested work. Done when: the change set contains only bounded edits and no adjacent improvement.
- Verify the changed behavior using the narrowest available check that exercises it, then inspect the final change set. Done when: the check passes, every addition retains concrete necessity, intent and failure behavior remain obvious, and no change lies outside the ask.
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.
- yesterday Changed · -12 tokens per session 54682f1082a2
- 4d ago First seen · 43 lines · 56 tokens per session scan A 51c31e91c568
minimalism-driven is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 858 once invoked, about $0.0002 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…