magi

magi is a skill for Claude Code from ladiossoop5star/open_magi. It costs 31 tokens per session (4,248 once invoked), scanned A, original, MIT.

A proposal-first discussion workflow in which three read-only agents research options while the main agent makes decisions, changes files, and verifies the result.

In plain words
What is it for?
It is for bug fixes and other coding tasks that need evidence, explicit acceptance criteria, verification commands, a chosen approach, and review of the actual changes.
Why use it?
It separates investigation, decision-making, implementation, and adversarial review, reducing the chance of fixing the wrong problem or trusting an unverified solution.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Claude Code.

Part of the open-magi plugin — 1 skill, 3 agents, 3 hooks shipped together

Good fit It is for bug fixes and other coding tasks that need evidence, explicit acceptance criteria, verification commands, a chosen approach, and review of the actual changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ladiossoop5star/open_magi/magi
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.

Any agent
npx skills add ladiossoop5star/open_magi --skill magi
Clone the repo
git clone --depth 1 https://github.com/ladiossoop5star/open_magi

Made for: Claude Code.

Or install open-magi, the plugin that ships this one along with the rest of its 1 skill, 3 agents, 3 hooks.

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 magi

README.md
[![agentmods](https://agentmods.dev/badge/skills/ladiossoop5star/open_magi/magi.svg)](https://agentmods.dev/skills/ladiossoop5star/open_magi/magi)
Your own site
<a href="https://agentmods.dev/skills/ladiossoop5star/open_magi/magi"><img src="https://agentmods.dev/badge/skills/ladiossoop5star/open_magi/magi.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,248 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00031 $0.04248
Opus 5 $0.00015 $0.02124
Sonnet 5 $0.00006 $0.00850
Haiku 4.5 $0.00003 $0.00425

Measured 7d ago against content hash 630560ec88d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

magi 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 7d 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.

adapters/claude/skills/magi/SKILL.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Magi

Overview

Run a coding-agent proposal-first deliberation loop. The main agent owns decisions, edits, verification, commits, rollback, and final reporting. Three read-only sub-agents only research and report.

Core rule: completion requires explicit acceptanceCriteria and verificationCommands, not confidence, plus an approved adversarial review of the actual diff before final-report.md.

Proposal-first rule: before any fix direction is selected, the main agent prepares an evidence packet and does not propose a fix. The deliberators propose directions first; the main agent selects one, then they review it before execution.

Council modes: the council runs in three modes sharing one launch and report mechanism. recon (round 1 Phase 1b) gathers evidence in parallel before the main agent commits to a direction. decision (Phases 2-4) selects the direction proposal-first. review (Phase 6) adversarially reviews the actual diff before completion. Track the active mode in state.json currentCouncilMode.

Required Reference Loading

These files are part of the skill contract. Load the listed reference before acting in that situation:

Situation Required reference
Starting or resuming Magi references/protocol.md
Creating checklist.md or changing phase references/checklist-template.md
Writing prompts, reports, synthesis, or verdict references/deliberation.md
Launching subagents or handling runtime adapter behavior references/runtime.md
Before any user-facing question references/question-firewall.md
Executing changes, verification, checkpoint, rollback, or next-round evidence references/execution-and-verification.md
Plugin repair, corrupt state, timeout, or repeated failure references/troubleshooting.md

Do not rely on memory for phase transitions. Before every phase transition, read .open_magi/magi-log/checklist.md.

When to Use

Use this skill when the user says start deliberation, magi, three sages, deliberation loop, loop until done, or requests repeated research -> synthesize -> act -> verify until completion.

Read the full file on GitHub · 390 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. 7d ago First seen · 390 lines · 31 tokens per session scan A 630560ec88d9

Subscribe to this mod's changes

magi is a skill published in the GitHub repository ladiossoop5star/open_magi (3 stars, last pushed 10d ago), licensed MIT. It adds 31 tokens to every session and 4,248 once invoked, about $0.0002 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 skills, from other repositories

opencode-ensemble

Use when coordinating multiple coding agents, delegating independent software work, managing OpenCode Ensemble teams, choosing teammate roles or models, reviewing teammate output, or deciding whether parallel execution is appropriate.

hueyexe/opencode-ensemble · 42 tokens

multi-bot

Coordinates responses between multiple GolemBot instances in a shared fleet. Use when the bot operates in a group chat with other bots, needs to decide whether to respond or pass, or must call a peer bot's API to fetch cross-domain data.

0xranx/golembot · 53 tokens

kb-guide

Search, read, create, and update knowledge base entries via MCP-connected KB tools. Use when the user asks to look up documentation, find existing articles, check if docs exist on a topic, create a new KB entry, update an existing document, or when domain questions should be answered from the knowledge base first.

0xranx/golembot · 66 tokens

escalation

Escalate unresolvable or sensitive requests to a human agent by recording an escalation entry. Use when the user asks to speak to a human, the bot cannot answer confidently, the request involves financial, legal, or security concerns, a safety issue is detected, or the user is frustrated after repeated failures.

0xranx/golembot · 66 tokens

fabric-rlm

Recursively decomposes oversized tasks into bounded child Pi agents with fresh context windows. Use for whole-repo audits, massive-context analysis, and multi-file refactors that do not fit one context.

monotykamary/pi-fabric · 44 tokens

fabric-supervisor

Starts a persistent Pi Fabric supervisor that watches the main session toward a concrete goal and steers only when needed. Use for long-running goal supervision without another extension.

monotykamary/pi-fabric · 36 tokens