omniplugin: Instructions file for Claude Code

CLAUDE.md

omniplugin CLAUDE.md is an instructions file for Claude Code from nagisanzenin/omniplugin. It costs 699 tokens per session, scanned A, original, MIT.

A set of instructions for building and maintaining plugins that work across several coding-agent platforms.

In plain words
What is it for?
Use it when creating a multi-platform plugin, adding support for another platform, or checking and updating the plugin's documentation and portability setup.
Why use it?
It gives agents a task-based route through the playbook and records rules for sharing core guidance while adapting platform-specific files.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions Claude Code; mentions Codex.

This is nagisanzenin/omniplugin's own configuration. It tells Claude Code how to work on omniplugin itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything omniplugin configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nagisanzenin/omniplugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nagisanzenin/omniplugin/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nagisanzenin/omniplugin

Made for: Claude Code.

Wrote 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.

agentmods badge for omniplugin CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nagisanzenin/omniplugin/claude-md.svg)](https://agentmods.dev/instructions/nagisanzenin/omniplugin/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nagisanzenin/omniplugin/claude-md"><img src="https://agentmods.dev/badge/instructions/nagisanzenin/omniplugin/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 699 This file is loaded in full into every session.
When invoked 699 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00699 $0.00699
Opus 5 $0.00349 $0.00349
Sonnet 5 $0.00140 $0.00140
Haiku 4.5 $0.00070 $0.00070

Measured 8d ago against content hash 0750c5492df0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

omniplugin CLAUDE.md 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 8d 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.

CLAUDE.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

omniplugin — agent instructions

This repo is a playbook that ships as a plugin: distilled guidance for building and maintaining omni-platform agent plugins, plus skills/omniplugin/SKILL.md (the installable router — Claude Code / Codex / Antigravity manifests are in .claude-plugin/, .codex-plugin/, root plugin.json; one repo, one shared core, native installs on many agentic platforms). The reference implementation behind every claim is https://github.com/nagisanzenin/engram — when this playbook and reality disagree, check engram's current main, then fix the playbook.

Route by task

You were asked to… Read, in order
Create a new omni-platform plugin docs/01-anatomy.mddocs/02-portability-rules.md, then the platform files for your launch targets. Copy templates/session-hook.sh patterns from day one — retrofitting portability is the expensive way.
Add a platform to an existing plugin docs/03-adding-a-platform.md (the checklist) + docs/platforms/<target>.md if it exists, else start from templates/platform-intake.md. Do Phase 1 research from primary sources even when a crib sheet exists — check its date first.
Release / maintain across platforms docs/04-maintenance.md; engram's RELEASE_PROTOCOL.md is the full reference implementation.
Debug a platform integration docs/05-pitfalls.md (it's probably in there) + the platform crib sheet.
Evaluate a new/unknown platform docs/platforms/landscape.md for the survey + templates/platform-intake.md for the questions.

Non-negotiables when applying this playbook

  1. Research the target platform's actual loader from primary sources before writing glue (schema, CLI changelog, flagship plugin). Never port by analogy.
  2. Check every new root-level path against every shipped platform's discovery conventions (namespace bleed — pitfall #2).
  3. Hooks: self-resolving, silent-unless-useful, degrade to silence, fail closed, exit 0.
  4. Ship honest status: Verified (with the platform version) vs Not-verified (with why it's harmless), in every install doc.
  5. The shared core stays byte-identical across platforms. Platform differences live in glue, waterfalls, and install docs — never as forks of core files.

Read the full file on GitHub · 29 lines

Changes

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.

  1. 8d ago First seen · 29 lines · 699 tokens per session scan A 0750c5492df0

Subscribe to this mod's changes

omniplugin CLAUDE.md is an instructions file published in the GitHub repository nagisanzenin/omniplugin (5 stars, last pushed 12d ago), licensed MIT. It adds 699 tokens to every session, about $0.0035 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens