agentmods.dev

zuvo CLAUDE.md

zuvo CLAUDE.md is an instructions file for coding agents from greglas75/zuvo. It costs 5,647 tokens per session, scanned B, original, MIT.

A skill for safely renaming code symbols or replacing function implementations across a codebase using Serena tools. A symbol is a named code element such as a function or class.

In plain words
What is it for?
Use it to rename functions or other symbols, change function signatures, replace function bodies, inspect affected references, and run relevant tests afterward.
Why use it?
It reduces missed references and unsafe text-based edits when changing code structure.

Instructions file

not rated 6 today B scan 5,647 tokens original MIT
View the source file greglas75/zuvo
Install

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.

agentmods
npx agentmods add instructions/greglas75/zuvo/claude-md
Clone the repo
git clone --depth 1 https://github.com/greglas75/zuvo

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 zuvo CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/greglas75/zuvo/claude-md.svg)](https://agentmods.dev/instructions/greglas75/zuvo/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/greglas75/zuvo/claude-md"><img src="https://agentmods.dev/badge/instructions/greglas75/zuvo/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,647 This file is loaded in full into every session.
When invoked 5,647 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
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 $0.05647 $0.05647
Opus 5 $0.02823 $0.02823
Sonnet 5 $0.01129 $0.01129
Haiku 4.5 $0.00565 $0.00565

Measured 3d ago against content hash 0e074f6cb599, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

zuvo CLAUDE.md scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`~/.claude/settings.json` and can persist its own older view afterwards, undoing the CLI's write.
CLAUDE.md · 354 lines

How it starts

The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zuvo Plugin — Project Guide

What this repo is

A Claude Code / Codex / Cursor / Antigravity / Kimi Code plugin. All skills are markdown files (SKILL.md). No TypeScript, no Python, no npm dependencies. package.json is metadata only (version field) — never run npm install.

Tech stack

Markdown. Shell scripts in scripts/. That's it.

How to update after making changes

For yourself (dev testing, no marketplace push)

./scripts/install.sh          # copies to Claude Code cache + Codex + Cursor + Antigravity + Kimi Code

Then restart Claude Code / Codex.

BUT — install.sh alone is NOT enough for Claude Code in all cases. Claude Code validates the plugin SHA from installed_plugins.json against the cache. If they don't match, skills may not load. To fully sync:

# Full local update (guaranteed to work):
./scripts/install.sh
claude plugin marketplace update zuvo-marketplace
claude plugin update zuvo@zuvo-marketplace
# Then restart Claude Code

One-command dev workflow (RECOMMENDED)

./scripts/dev-push.sh "description"

This does EVERYTHING in one command:

  1. git add -A + commit with your message
  2. git push origin main
  3. Update marketplace SHA → push marketplace
  4. Update installed_plugins.json SHA (fixes the stale SHA problem)
  5. Copy files to Claude Code cache (all directories)
  6. Build + install to Codex

After running: just restart Claude Code. No uninstall/install needed.

For end users (marketplace release)

./scripts/release.sh patch "description"

This does everything: version bump, commit, push, tag, marketplace SHA update. Users get it via claude plugin update zuvo.

Quick reference

What you want Command
Push + sync everything (dev) ./scripts/dev-push.sh "description" then restart Claude/Codex
Test changes locally (dev) ./scripts/install.sh then restart Claude/Codex/Cursor/Kimi
Release to users ./scripts/release.sh patch "msg"
Verify release works claude plugin uninstall zuvo@zuvo-marketplace && claude plugin install zuvo then new session
User first install claude plugin marketplace add greglas75/zuvo-marketplace && claude plugin install zuvo
User updates claude plugin marketplace update zuvo-marketplace && claude plugin update zuvo@zuvo-marketplace

Read the full file on GitHub · 354 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. 3d ago First seen · 354 lines · 5,647 tokens per session scan B 0e074f6cb599

Subscribe to this mod's changes

zuvo CLAUDE.md is an instructions file published in the GitHub repository greglas75/zuvo (6 stars, last pushed today), licensed MIT. It adds 5,647 tokens to every session, about $0.0282 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code reviewTestingai-codingclaude-codeclaude-code-plugincode-qualitycodex
Related

Other instructions, from other repositories

roam-code AGENTS.md

Instructions for Cranot/roam-code, covering agents.md — roam-code development guide, what this project is, documentation hub, where files go (private vs public) and quality discipline (from internal/dogfood/ + agi-in-md).

Cranot/roam-code · 14,242 tokens

plan-forge dapr.instructions.md

Dapr patterns for .NET — building blocks, component config, sidecar architecture, multi-tenant isolation, workflows, state management, secrets.

srnichols/plan-forge · 4,968 tokens

plan-forge copilot-instructions.md

Copilot instructions for srnichols/plan-forge, covering instructions for copilot, architecture principles, core principles (non-negotiable), cost estimates and talking to forge-master.

srnichols/plan-forge · 2,670 tokens

plan-forge testing.instructions.md

Testing rules for Plan Forge — vitest patterns, fake-timers vs tolerance, mocking conventions, and how to read test output without hallucinating failures. Auto-loads when editing test files.

srnichols/plan-forge · 3,216 tokens

plan-forge landing-zone.instructions.md

Azure Landing Zone baselines — identity, network, policy, management, security, tagging, subscription organization.

srnichols/plan-forge · 2,228 tokens

plan-forge policy.instructions.md

Azure Policy and Initiative compliance — definitions, assignment, compliance state, exemptions, remediation tasks.

srnichols/plan-forge · 2,019 tokens