What is agenta-plugin CLAUDE.md?

A set of instructions for using the Agenta plugin in Claude Code, a coding assistant that can access configured tools. It explains which tools to choose for tasks such as documentation lookup, web fetching, file editing, data storage, and research.

Use it to guide tool selection and project procedures when working in the Agenta plugin repository, including looking up libraries, fetching web pages, editing files, storing structured data, searching papers, and maintaining documentation.

It gives the assistant a consistent order for choosing tools and highlights project-specific rules, such as clarifying certain requests and maintaining its knowledge base. The excerpt does not describe an automated coding feature.

How agentalabs/agenta-plugin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to agentalabs/agenta-plugin. 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/agentalabs/agenta-plugin/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/agentalabs/agenta-plugin

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/agentalabs/agenta-plugin/claude-md/github.svg)](https://agentmods.dev/instructions/agentalabs/agenta-plugin/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/agentalabs/agenta-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/agentalabs/agenta-plugin/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/agentalabs/agenta-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/agentalabs/agenta-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 719 This file is loaded in full into every session.

When invoked 719 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.

Model	Per session	Once invoked
Fable 5.1	$0.00719	$0.00719
Opus 5.5	$0.00288	$0.00288
Sonnet 5.5	$0.00144	$0.00144
Haiku 4.5	$0.00072	$0.00072

Measured 2mo ago against content hash 995d6f15215e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agenta-plugin 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 2mo 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agenta Plugin — Agent Instructions

This project uses Agenta Plugin. The .mcp.json file configures which MCP servers are available as tools.

Tool Usage Priority

When completing tasks, use the best tool available — native Claude Code tools are often sufficient:

Need	Best tool	When to escalate
Look up library docs	Context7 or mcpdoc	—
Simple web search	WebSearch (native)	Omnisearch for multi-engine research
Fetch a URL	WebFetch (native)	Crawl4AI for anti-bot sites, Puppeteer for JS-rendered pages
Read/write/edit files	Read, Write, Edit (native)	—
Search file contents	Grep, Glob (native)	—
Store structured data	SQLite, Supabase, or Postgres	—
Store embeddings	Qdrant or Claude Context	—
Track entities & relations	MemoryGraph	—
Run untrusted code	E2B or Daytona sandbox	—
Scrape web pages	Crawl4AI	Puppeteer for JS-rendered pages
Search academic papers	Consensus	—
Manage context window	Context Mode	—
Persistent cross-session memory	Memsearch	—
Ingest sources into KB	Skill Seekers	—

Important

Always clarify with the user if something is unclear before proceeding.

Knowledge Base Maintenance

If this project maintains a knowledge base, follow these patterns:

Source registry

Maintain a source registry in SQLite tracking each data source:

Source name, type (rss, api, webpage, file, database), URL/path
Sync schedule (daily, weekly, on-demand)
Last sync timestamp and content hash
Status (active, error, disabled)

Incremental sync

On each maintenance run:

Query the source registry for sources due for sync
For each source: fetch content, compare hash to last known hash
Skip unchanged sources entirely
For changed sources: chunk, embed, deduplicate (similarity > 0.95 = skip), upsert
Update the registry with new timestamp and hash
Log: sources_checked, items_added, items_skipped, errors

Read the full file on GitHub · 78 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.

2mo ago First seen · 78 lines · 719 tokens per session scan A 995d6f15215e

Subscribe to this mod's changes

agenta-plugin CLAUDE.md is an instructions file published in the GitHub repository agentalabs/agenta-plugin (2 stars, last pushed 7mo ago), licensed MIT. It adds 719 tokens to every session, about $0.0029 per session on Opus 5.5. 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.

agenta-plugin CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agenta-plugin CLAUDE.mdagentalabs/agenta-plugin	Instructions file	2	7mo ago	MIT	A	719	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
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
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	3d ago	MIT	A	4,313	Codex, OpenCode

agenta-plugin: Instructions file for Claude Code