What is resolve-ai-plugins CLAUDE.md?

A set of writing and design rules for building Resolve AI plugins for Claude Code. It explains what belongs in a workflow skill and what belongs in a tool or server.

Use it when creating or reviewing Resolve AI plugin skills, tools, prompts, confirmations, and output behavior.

It helps keep plugin guidance stable, clear, and within the host's limits. It also prevents changing API details from being mixed into user-facing workflow instructions.

How resolve-ai-oss/resolve-ai-plugins configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to resolve-ai-oss/resolve-ai-plugins. 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/resolve-ai-oss/resolve-ai-plugins/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/resolve-ai-oss/resolve-ai-plugins

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/resolve-ai-oss/resolve-ai-plugins/claude-md/github.svg)](https://agentmods.dev/instructions/resolve-ai-oss/resolve-ai-plugins/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/resolve-ai-oss/resolve-ai-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/resolve-ai-oss/resolve-ai-plugins/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/resolve-ai-oss/resolve-ai-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/resolve-ai-oss/resolve-ai-plugins/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 508 This file is loaded in full into every session.

When invoked 508 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 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00508	$0.00508
Opus 5.5	$0.00203	$0.00203
Sonnet 5.5	$0.00102	$0.00102
Haiku 4.5	$0.00051	$0.00051

Measured 1mo ago against content hash 9db0d6602f45, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

resolve-ai-plugins 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 1mo 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.

Origin

This is a copy

100% identical to resolve-ai-plugins AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resolve AI Plugin Guidance

Skill vs Tool Description Boundary

Skills are shipped less often than MCP tools and server behavior. Keep skills focused on stable workflow guidance:

When to use a workflow and when to hand off to another skill.
How to translate user intent into the right class of tool call.
How to compose high-quality prompts/messages from local context.
Human-facing output shape and follow-up behavior.
Confirmation gates for mutating or credit-consuming actions.
Host-specific execution hints only when the host truly differs.

Put volatile or API-specific details in MCP tool descriptions or server-side code instead:

Exact parameters, enums, defaults, limits, sort order, and return fields.
Stream protocol details, including terminal markers and failure semantics.
REST endpoints, payload schemas, authentication, and feature gates.
Current backend limitations or behavior that can change independently of plugin releases.
Tool-specific examples that are mostly schema examples rather than workflow examples.

Shared stream-command behavior belongs in the MCP server instructions, condensed; ask carries the full execution semantics since tool descriptions arrive complete at call time. Other tool descriptions should only say whether the tool returns a stream_command and what live state it follows.

If a skill starts restating a tool schema, trim the skill and improve the server instructions or tool description instead.

Host size limits

Hosts truncate MCP guidance text: Claude Code cuts server instructions and each tool description at 2KB; Codex prioritizes the first 512 characters of instructions. Keep server instructions under 2KB with the most important guidance first (enforced by packages/svc-mcp-server/src/__tests__/v2HttpTransport.test.ts). Never duplicate text between instructions and a tool description — the instructions copy is the one at truncation risk, so it should hold only cross-tool guidance.

Read the full file on GitHub · 46 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.

1mo ago Changed · +1 tokens per session 9db0d6602f45
2mo ago First seen · 46 lines · 507 tokens per session scan A 952273058c3c

Subscribe to this mod's changes

resolve-ai-plugins CLAUDE.md is an instructions file published in the GitHub repository resolve-ai-oss/resolve-ai-plugins (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 508 tokens to every session, about $0.0020 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to resolve-ai-plugins AGENTS.md, differing in 0 lines, and is treated as a copy.

Building agents

resolve-ai-plugins CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
resolve-ai-plugins CLAUDE.mdresolve-ai-oss/resolve-ai-plugins	Instructions file	4	yesterday	Apache-2.0	A	508	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

resolve-ai-plugins: Instructions file for Claude Code