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-codebase-perspectivegit 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-codebase-perspective)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/from-codebase-perspective"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/from-codebase-perspective/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-codebase-perspective"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/from-codebase-perspective.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 | $0.00040 | $0.00612 |
| Opus 5 | $0.00020 | $0.00306 |
| Sonnet 5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
from-codebase-perspective 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 3d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
From codebase perspective
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants an answer only from the codebase seat (what existing code tolerates or punishes). |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Returns a codebase-perspective analysis in chat. |
| Done | Returns a codebase-perspective answer without blending. |
Not for
- Rebuilding a design from primitives: use from-first-principle.
- Blended multi-seat analysis: run each from-*-perspective seat independently and compare after.
- Source or remote mutation: this skill is read-only.
Inputs
The question or proposal to analyze from the codebase seat. The codebase under analysis must be readable in the working tree; if it is not reachable, stop and report that the seat has no evidence.
Procedure
- Confirm the seat is codebase only. State that money, customers, timing, impact, career, breaking, rent-seeking, innovation, stability, moat, human, and skeptic perspectives are out of scope. Done when: the out-of-scope seats are named.
- Read the existing code, structure, conventions, and constraints that bear on the question. Done when: the relevant code is read and the evidence base is stated.
- Determine what the existing code tolerates: patterns, shapes, and directions it already accepts without friction. Done when: tolerates patterns are listed with code evidence.
- Determine what the existing code punishes: patterns, shapes, and directions that fight the current structure, require rework, or break invariants. Done when: punishes patterns are listed with code evidence.
- Emit the answer strictly from the codebase seat. Do not blend any other perspective; if another seat is relevant, name it as a separate lens to run independently. Done when: a codebase-perspective answer is emitted without blended content.
Failure and recovery
- Unreachable codebase: stop. Report that the codebase seat has no evidence and emit no analysis.
- Question outside the codebase seat: stop. Name the seat the question belongs to and emit no codebase answer.
- Pressure to blend lenses mid-answer: refuse. The non-blending rule is load-bearing; comparison happens only after independent outputs.
- Partial evidence: emit only the portion grounded in read code and label the rest as unverified. Never present inference as observed code behavior.
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.
- 3d ago First seen · 45 lines · 40 tokens per session scan A 041069feef38
from-codebase-perspective is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 612 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 2026-09-06.
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…