What is agent-smith CLAUDE.md?

Repository instructions for Agent Smith, a shared skill distributed to Claude Code, Codex, and Cursor. They define how its plugin packages, marketplace listings, versions, indexes, and validation must agree.

Use them when developing, packaging, validating, or releasing Agent Smith plugins and their marketplace entries.

They keep the same skill source and metadata consistent across different coding-agent systems. They also ensure unavailable runtime tests are reported accurately instead of being treated as passed.

How supernova-labs/agent-smith configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to supernova-labs/agent-smith. 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/supernova-labs/agent-smith/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/supernova-labs/agent-smith

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/supernova-labs/agent-smith/claude-md/github.svg)](https://agentmods.dev/instructions/supernova-labs/agent-smith/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/supernova-labs/agent-smith/claude-md"><img src="https://agentmods.dev/badge/instructions/supernova-labs/agent-smith/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/supernova-labs/agent-smith/claude-md"><img src="https://agentmods.dev/badge/instructions/supernova-labs/agent-smith/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 462 This file is loaded in full into every session.

When invoked 462 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	$0.00462	$0.00462
Opus 5.5	$0.00185	$0.00185
Sonnet 5.5	$0.00092	$0.00092
Haiku 4.5	$0.00046	$0.00046

Measured 2mo ago against content hash a1a6c9f3d522, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-smith 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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Smith — Development Guide

This repository distributes the same Agent Smith skill to Claude Code, Codex, and Cursor.

Invariants

agent-smith/skills/agent-smith/ is the single canonical skill source.
Root marketplace manifests for Claude, Codex, and Cursor all resolve to agent-smith/.
Native plugin manifests live under agent-smith/ and consume the same skill tree.
All plugin manifests must agree on name and version.
agent-smith/skills/agent-smith/SKILL.md must use portable frontmatter and stay below 500 lines.
Harness-specific formats belong in references, templates, or manifests rather than the shared workflow.
.agent-smith/index.json uses schema 2.0 and must cover every component/target pair.
Validation must report unavailable runtime smoke tests as not run, not passed.

Important paths

.claude-plugin/marketplace.json — Claude marketplace catalog
.agents/plugins/marketplace.json — Codex marketplace catalog
.cursor-plugin/marketplace.json — Cursor marketplace catalog
agent-smith/ — installable plugin package shared by all catalogs
agent-smith/skills/agent-smith/SKILL.md — portable workflow
agent-smith/skills/agent-smith/references/ — architecture and harness references
agent-smith/skills/agent-smith/scripts/ — deterministic inspection, migration, and validation
agent-smith/skills/agent-smith/references/templates/ — portable and harness-specific templates
tests/ — isolated repository fixtures and regression tests

Validation

bash agent-smith/skills/agent-smith/scripts/validate.sh
python3 -m unittest discover -s tests -v

For runtime verification, load or install the repository separately in Claude Code, Codex, and Cursor. Authentication-dependent checks are release requirements but must remain distinct from structural validation.

Releases

Keep all three plugin manifest versions synchronized.
Update CHANGELOG.md for every release.
Validate the repository before tagging.
Record structural and runtime results for all targets.

Read the full file on GitHub · 43 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 · 43 lines · 462 tokens per session scan A a1a6c9f3d522

Subscribe to this mod's changes

agent-smith CLAUDE.md is an instructions file published in the GitHub repository supernova-labs/agent-smith (9 stars, last pushed 3mo ago), licensed MIT. It adds 462 tokens to every session, about $0.0018 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.

Building agents

agent-smith CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-smith CLAUDE.mdsupernova-labs/agent-smith	Instructions file	9	3mo ago	MIT	A	462	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

agent-smith: Instructions file for Claude Code