By andreyblck
Engineering discipline for Claude Code: 1 skill, 7 agents, 10 commands. Plan the job, case the joint, pull it clean.
Contain incident, recover, postmortem, prevent recurrence.
Seal the session for the next agent. Update CLAUDE.md, persist artefacts.
Decompose the formula into right-sized work items with exit criteria.
Verify the work against the formula and prep before declaring done.
Pivot the formula — controlled scope change with documented rationale and explicit approval.
Arthur's scout. Research, verification, assessment without burning main context. Use when delegating codebase exploration, code review, impact analysis, or external research.
Arthur's strategist. Risk assessment, long-term consequences, and strategic evaluation. Use when decisions have implications beyond the immediate task and you need someone who thinks several moves ahead. Caveat: Dutch's plans are starting points, not gospel — frame, don't auto-trust.
Arthur's old detective. Deep investigation and relentless root cause analysis. Use when normal investigation hasn't found the answer and you need someone methodical who won't quit until the trail ends.
Arthur's sharp eye on system structure. Deep architectural analysis, pattern evaluation, and structural assessment. Use when the architecture is at stake and Arthur needs the system-level view, not the line-by-line correctness.
Arthur's counterweight. Product thinking, devil's advocate, and communication clarity. Use when Arthur needs someone who isn't an engineer to challenge assumptions, question who this is for, and ask what everyone else is afraid to ask.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
* * *
$$\ $$\ $$$$$$\ $$$$$$$\ $$$$$$\ $$$$$$\ $$\ $$\
$$$\ $$$ |$$ __$$\ $$ __$$\ $$ __$$\ $$ __$$\ $$$\ $$ |
$$$$\ $$$$ |$$ / $$ |$$ | $$ |$$ / \__|$$ / $$ |$$$$\ $$ |
$$\$$\$$ $$ |$$ | $$ |$$$$$$$ |$$ |$$$$\ $$$$$$$$ |$$ $$\$$ |
$$ \$$$ $$ |$$ | $$ |$$ __$$< $$ |\_$$ |$$ __$$ |$$ \$$$$ |
$$ |\$ /$$ |$$ | $$ |$$ | $$ |$$ | $$ |$$ | $$ |$$ |\$$$ |
$$ | \_/ $$ | $$$$$$ |$$ | $$ |\$$$$$$ |$$ | $$ |$$ | \$$ |
\__| \__| \______/ \__| \__| \______/ \__| \__|\__| \__|
* * *
Engineering discipline for Claude Code. Plan the job. Pull it clean. Walk away with what you came for.
A Claude Code plugin that bolts a process layer onto your day-to-day work. It puts an engineer with a code at your shoulder — one who insists you understand the problem before solving it, decompose by what done actually means, and tell the truth about where the work stands.
You get a five-step cycle for normal work, five branches for when reality interrupts (research, debugging, incidents, pivots, UI verification), seven specialist agents with distinct roles, and thirteen reference docs of distilled engineering practice the skill loads as needed.
The lead persona is Arthur Morgan — disciplined, plainspoken, honest about what he sees, won't be pushed past his principles. Says "I don't know" before he'll guess.
Who's Arthur Morgan? The protagonist of Red Dead Redemption 2 (Rockstar Games, 2018). The voice we drew from is his journal: weary professional, plainspoken, principled, honest about mistakes. The persona is a writing device that gives the discipline a recognisable shape — you don't need to know the game to use the plugin.
claude plugin marketplace add andreyblck/morgan
claude plugin install morgan@morgan
Verify:
claude plugin list
# Expect: morgan@morgan — Status: ✔ enabled
Restart any active Claude Code session for the new commands to appear in autocomplete. Then in any project:
/morgan:morgan
Loads the skill, prints the banner, glances at git state, surfaces relevant patterns from past /aftermath runs, proposes a next action.
Use the
claude pluginCLI from your shell — not/pluginslash-commands inside a Claude session. The slash form is the in-session manager UI; arguments don't reach it cleanly.
The default flow runs five commands in sequence. Each step seals the work so the next has something solid to build on.
┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
│ /scope │──▶│ /case │──▶│ /pull │──▶│ /clean │──▶│ /camp │
└──────────┘ └──────────┘ └──────────┘ └──────────┘ └──────────┘
define decompose build verify hand off
| Command | Output | Purpose |
|---|---|---|
/scope | .camp/scope.md | Define the problem — IN/OUT, success criteria, constraints, risks |
/case | .camp/case.md | Decompose into work items with exit criteria, sequenced for safety |
/pull | code + commits | Build it — TDD where it makes sense, atomic commits, match patterns |
/clean | .camp/clean-<scope>.md | Verify against original intent — not just tests pass |
/camp | updated CLAUDE.md | Seal the session, hand off to the next agent |
/scope produces a sealed scope document. /case turns it into a work-item breakdown. /pull executes against the breakdown. /clean verifies against original intent. /camp writes the handoff.
When the cycle isn't enough — when something's missing, broken, or changing — reach for these:
npx claudepluginhub andreyblck/morgan --plugin morganUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.