By flexion
Behavioral skills for Claude Code - critical assessment, evidence-based debugging, and rule authoring
Perform structured critical assessment of a proposal, approach, design, or solution. Use when evaluating ideas, reviewing approaches, comparing options, giving feedback on plans, or when asked "what do you think" about any technical decision. Triggers on proposals, suggestions, architecture decisions, tradeoff analysis, design review, and solution evaluation.
Create a compact frontmatter rule from verbose markdown
Anti-sycophancy behavioral check. Use BEFORE agreeing with any user proposal, suggestion, or approach. Triggers when the user says "let's do X", "I think we should", "how about", "what if we", proposes a solution, presents an architecture, suggests a change, or asks for agreement on any technical decision. Also triggers when you notice yourself about to say "great idea", "that sounds good", "sure", or any form of agreement without prior analysis.
Evidence-based debugging workflow for errors, bugs, crashes, and unexpected behavior. Use when diagnosing failures, investigating stack traces, fixing broken builds, resolving test failures, or when something stopped working. Triggers on error messages, exceptions, stack traces, debugging sessions, and troubleshooting any technical issue.
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.
Your strategic coding partner.
Like a cycling domestique, it carries the water, stays focused on your goals, and handles the unglamorous work you don't want to do.
"Remember Sammy Jankis."
Like Leonard in Memento, Claude can't form long-term memories. Context window fills up, conversation resets, everything vanishes. memento gives Claude its tattoos—session files that persist decisions, progress, and context across resets.
Helps developers embody Flexion fundamentals across conversation boundaries:
"I told you. You agreed. You forgot. Repeat."
You've written the perfect CLAUDE.md. Claude reads it. Claude agrees. By turn 47, Claude ignores half of it. mantra provides curated behavioral rules that are automatically loaded via Claude Code's native .claude/rules/ mechanism—ensuring consistent behavior from turn 1 to turn 100.
Helps developers embody Flexion fundamentals throughout long sessions:
"The burden is mine now."
JIRA tickets, Azure DevOps work items, commit messages, PR descriptions. The awful-but-important work that kills your flow. onus handles the project management bureaucracy so you can code.
Supports GitHub Issues (default, zero-config), JIRA, and Azure DevOps work items.
Helps developers embody Flexion fundamentals while staying in flow:
External (GitHub/JIRA/Azure DevOps)
│
▼ fetch issue details
[onus]
│
▼ populate session file
[memento] ←── "What's next?" lookup
│
▼ read session context
[mantra] ──► native rules auto-loaded
Each plugin works standalone but gains enhanced behavior when used together.

Session resumption showing mantra (context refresh counter), onus (issue tracking), and memento (session file) working together. Claude reads the session file and picks up exactly where the previous conversation left off.
| Tool | Version | Used By | Purpose |
|---|---|---|---|
| Claude Code | 2.0.12+ | All | Plugin host (plugin system introduced in v2.0.12) |
| Node.js | 18+ | All | Runtime for hooks and scripts |
| git | 2.x | All | Branch detection, commits, session tracking |
When using /onus:fetch, Claude will use these tools to retrieve work items:
| Tool | Platform | Purpose |
|---|---|---|
| GitHub CLI (gh) | GitHub | Fetch issues, create PRs (recommended) |
| Claude's WebFetch | JIRA, Azure DevOps | Built-in HTTP tool for API calls |
Note: For JIRA/Azure DevOps, Claude uses its built-in WebFetch capability. No additional tools required.
| Variable | Platform | How to Get |
|---|---|---|
GITHUB_TOKEN | GitHub | Create PAT with repo scope |
JIRA_TOKEN | JIRA | echo -n "email:api_token" | base64 (Get API token) |
AZURE_DEVOPS_TOKEN | Azure DevOps | echo -n ":pat" | base64 (Create PAT with Work Items Read) |
# Check required tools
git --version # git version 2.x
node --version # v18.x or higher
claude --version # Claude Code 2.x
# Check GitHub CLI (optional, for onus with GitHub)
gh --version # gh version 2.x
gh auth status # Verify authentication
/plugin marketplace add flexion/claude-domestique
npx claudepluginhub flexion/claude-domestique --plugin mantraSession management for Claude Code - auto-injected via hooks, zero config
Work item automation for Claude Code - auto-injected via hooks, zero config
Agent Artifex — designing and testing MCP servers, agents, chatbots, and tool-calling systems using evidence-based patterns from Anthropic, OpenAI, RAGAS, and academic research
Opinionated workflow guides and best practices - the preacher's proven patterns for Claude Code projects
Automatic context engineering — observes your coding sessions and generates rules, suggestions, skills, and hooks so Claude gets smarter on your codebase over time
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Efficient skill management system with progressive discovery — 410+ production-ready skills across 33+ domains
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses