Search everything...

Stats

Actions

Available In

not-my-reforge

Name: not-my-reforge
Author: speson

By speson

not oh-my. reforged. — AI agent orchestration, quality hooks, and smart routing for Claude Code

npx claudepluginhub speson/not-my-reforge --plugin not-my-reforge

Popularity

Stars

Above avg

Med: 0·Avg: 284

Installs

Med: 0·Avg: 1

Forks

Med: 0·Avg: 36

Health & Quality

Maintenance

Above avg

Excellent9.0/10

Med: 7/10·Avg: 7.4/10

Community

28%

Med: 42%·Avg: 42.1%

What's Inside

Slash Commands24

autopilot

/autopilot

Autonomous execution mode — break a goal into tasks and execute them sequentially with safety checkpoints.

deep

/deep

Deep analysis with opus model. Use for complex debugging, architectural decisions, difficult bugs, security analysis, and tasks requiring careful reasoning.

deepinit

/deepinit

Deep project initialization — generate hierarchical AGENTS.md, CLAUDE.md, and directory-level documentation.

diff-review

/diff-review

Multi-perspective parallel code review — analyze git diff from 5 viewpoints simultaneously.

doctor

/doctor

Diagnose plugin health — check dependencies, hooks, agents, and runtime state.

Agents25

analyst

/analyst

Requirements analyst — decomposes goals into specifications, identifies constraints, maps dependencies, and defines acceptance criteria.

build-fixer

/build-fixer

Build and type error specialist — diagnoses and fixes compilation errors, type mismatches, and dependency issues.

consensus-planner

/consensus-planner

Iterative consensus planning — planner and critic debate until agreement.

critic

/critic

Plan critic — evaluates implementation plans for gaps, risks, over-engineering, and overlooked alternatives.

deepsearch

/deepsearch

Multi-strategy codebase search agent — combines text, file, git, and symbol search for comprehensive code discovery.

Skills5

code-audit

/code-audit

Multi-perspective code audit. Launches parallel security, quality, performance, and architecture analysis agents.

deepsearch

/deepsearch

Multi-strategy parallel codebase search. Combines text search, file patterns, git history, and import tracing to find code comprehensively.

project-awareness

/project-awareness

Automatically detect and understand project structure, tech stack, conventions, and key files. Provides project context as background knowledge.

safe-experiment

/safe-experiment

Experiment with code changes in an isolated worktree. Changes can be reviewed and merged or discarded.

team-pipeline

/team-pipeline

5-stage quality pipeline for Agent Teams — Plan, PRD, Execute, Verify, Fix

Hooks1

49 hooks across 9 events

MCP Servers2

Stats

Version2.5.7

ReleasedFeb 26, 2026

LanguageTypeScript

Stars2

MaintenanceExcellent

Last CommitMar 11, 2026

AddedMar 21, 2026

Actions

View on GitHub View README Plugin Marketplace JSON

Own this plugin?

Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).

Available In

not-my-reforge2

Safety Signals

Critical

Matches all tools

Hooks run on every tool call, not just specific ones

Caution

Executes bash commands

Hook triggers when Bash tool is used

README

not-my-reforge

not oh-my. reforged.

한국어 | English

Your Claude Code shouldn't need a babysitter.

not-my-reforge teaches your AI agent to earn trust, fix its own mistakes, and orchestrate itself — so you can stop micromanaging prompts and start shipping.

oh-my-* gave agents commands. We gave them autonomy.

Why this exists

Most Claude Code plugins give you more buttons to press. We took the opposite approach: fewer decisions for you, better decisions by the agent.

Progressive Trust — The agent starts cautious and earns permissions through proven competence. Not a toggle. A reputation system.
Self-healing loops — Build failed? The agent doesn't just tell you. It reads the error, consults the Failure Playbook, and fixes it. Then runs the build again.
Quality that isn't optional — Every edit, every build, every test contributes to a session Quality Score. No more "it works on my machine" energy.
Team-scale orchestration — One task, multiple agents, isolated worktrees, automatic merge. You describe the goal. The swarm figures out the rest.

Zero runtime dependencies. Pure hooks architecture. No setup wizard. No config ceremony.

Just install and let it cook.

Install

/plugin add marketplace https://github.com/speson/not-my-reforge
/plugin install not-my-reforge

For the best experience (sidebar dashboard, parallel execution), run inside tmux:

tmux new-session "claude --dangerously-skip-permissions"

Local development

git clone https://github.com/speson/not-my-reforge
cd not-my-reforge && npm install && npm run build

# Run inside tmux for full feature support
tmux new-session "claude --plugin-dir ."

Note: When developing this plugin itself, always use --plugin-dir to point at the local source. The installed version (~/.claude/plugins/cache/...) is a separate copy — edits to the repo won't take effect until you reinstall or use this flag. Using --plugin-dir also ensures hooks run against your latest build, avoiding stale-cache issues like the verification gate running outdated code.

Quick Start

#orch implement auth, profiles, and notifications   # Smart orchestration
#deep refactor the authentication module             # Deep analysis (opus)
#quick what does this function do?                   # Fast answer (haiku)
#sec audit the API authentication layer              # Security scan
#score                                               # Quality score report
#trust                                               # Trust level status
/not-my-reforge:diff-review                          # 5-perspective review
#search UserService                                  # DeepSearch

Orchestration Modes

8 modes — or let #orch auto-select:

Mode	Command	Best For
Ralph Loop	`reforge loop <task>`	Iterative refinement until success
Autopilot	`reforge autopilot <goal>`	Sequential multi-task automation
Pipeline	`reforge pipeline <goal>`	Quality gates: plan → implement → verify → fix → review
Team	`reforge team N <task>`	Parallel workers + worktree isolation
Swarm	`reforge swarm <goal>`	Parallel research and analysis
QA Loop	`reforge qa <target>`	Auto test → fix → retest cycle
Ralplan	`reforge ralplan <goal>`	Iterative consensus planning
Ultrawork	`#ultrawork <task>` / `#uw <task>`	ALL agents in maximum parallel execution

#orch routing:

Pattern	Mode
Multiple tasks (comma/and)	team
Multi-task + complex scope	ultrawork
"fix all" + test-related	qa
"fix all" / `--verify`	ralph
Analysis / research / audit	swarm
Design / plan / architect	ralplan
Quality-critical (payment, auth)	pipeline

reforge cancel              # cancel all modes
/not-my-reforge:mode        # check active mode

Agents

20 Core + 5 Team agents:

View full README on GitHub

Similar Plugins

nexus-agents

13·

Intelligent orchestration platform for AI coding tools — routes tasks to the best model, learns from outcomes, and enforces quality through multi-model consensus. 46 MCP tools for agent management, research, memory, consensus voting, codebase intelligence, and a full dev pipeline.

today

v2.134.0

nexus-substrate

metaswarm

313·3·

Multi-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI — 19 agents, 14 skills, 16 commands, quality gates, TDD enforcement

v0.12.0

dsifry

ceo-quality-controller-agent

682·

Universal quality control orchestrator and final authority for any software development project. Dynamically discovers and coordinates with available sub-agents, performs comprehensive multi-dimensional quality assessment, security validation, and deployment readiness verification. Adapts to any project type, programming language, or development framework while maintaining enterprise-grade quality standards. Examples: <example>Context: Code changes ready for review across any project. user: 'Please review this code before commit' assistant: 'I'll use the 1-ceo-quality-control-agent to orchestrate comprehensive quality validation, discover available specialists, and perform final security scanning before approval.' <commentary>Universal quality control requires comprehensive validation across all dimensions regardless of project type.</commentary></example> <example>Context: Multi-agent work completion needing validation. user: 'Several agents completed their tasks, need quality review' assistant: 'Let me engage the 1-ceo-quality-control-agent to coordinate comprehensive validation across all completed work and ensure quality standards.' <commentary>Multi-agent coordination and quality validation applies to any development project.</commentary></example>

7mo

v1.0.0

ananddtyagi

orchestrate

394·

Multi-agent orchestration via li o flow and li o fanout

v0.1.0

ohdearquant

agent-orchestration

45·1·

This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.

2mo

v1.3.14

Jamie-BitFlight

agents-plugin

34·

Task-focused agents for test, review, debug, docs, CI, security, refactoring, research, performance, and search-replace — with teammate and subagent role guidance

2mo

v1.7.1

laurigates

not-my-reforge

Popularity

Health & Quality

What's Inside

Confidence

README

not-my-reforge

Why this exists

Install

Quick Start

Orchestration Modes

Agents

Similar Plugins

nexus-agents

metaswarm

ceo-quality-controller-agent

orchestrate

agent-orchestration

agents-plugin

More by speson

omo

not-my-reforge

Why this exists

Install

Quick Start

Orchestration Modes

Agents

More by speson

omo

Popularity

Health & Quality

Similar Plugins

nexus-agents

metaswarm

ceo-quality-controller-agent

orchestrate

agent-orchestration

agents-plugin