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 from-first-principlegit 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/from-first-principle)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/from-first-principle"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/from-first-principle/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/from-first-principle"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/from-first-principle.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 | $0.00064 | $0.00707 |
| Opus 5 | $0.00032 | $0.00353 |
| Sonnet 5 | $0.00013 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
from-first-principle 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 6d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
From first principle
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants to rebuild a design, organization, or API from primitives. |
| Authority | Write one named local rebuild specification artifact; read the existing target as read-only. Rollback is deleting the artifact. |
| Side effect | Writes a first-principles rebuild specification of the design, organization, or API to a local file. |
| Done | Produces a rebuilt first-principles specification naming primitives, derived structure, and open assumptions. |
Not for
- A perspective take on a question — use the from-*-perspective seats.
- Pruning an existing structure down to its primitives — this rebuilds from primitives, it does not strip down.
- Restarting from a blank greenfield — use fromzero.
- Remote, credential, publish, deploy, or irreversible changes.
Inputs
Required: the target to rebuild (a design, an organization, or an API) and access to its current form for read-only comparison. Optional: the primitives the user insists on starting from; when absent, primitives are derived from the target itself.
Procedure
- Name the target and confirm whether it is a design, an organization, or an API. Done when: the target type is stated.
- Enumerate the irreducible primitives the target cannot exist without: concepts, data, or operations that are not themselves derivable from something smaller in this target. Done when: primitives are listed and each is confirmed irreducible.
- Derive the target's structure from those primitives only. Reject any element that is not forced by a primitive or a necessary composition of primitives. Done when: every derived element traces to a primitive or composition.
- For each derived element, record the primitive or composition that forces it. Elements with no primitive basis are open assumptions, not derived. Done when: each element is labeled derived or open-assumption with its basis.
- Write the rebuild specification to a local artifact: the enumerated primitives, the derived structure, each derivation step, and the open assumptions. Done when: the artifact is written with all four sections.
- Diff the rebuilt structure against the existing target, marking what changed and what was eliminated as non-primitive. Done when: the diff is recorded in the artifact.
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.
- 6d ago First seen · 47 lines · 64 tokens per session scan A 6e73d5bec9e4
from-first-principle is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 707 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…