Instructions file CodexOpenCode
Instructions for rlaope/nen: The nen abilities (https://github.com/rlaope/nen): one per Nen category, hatsu (forging new skills) at the center, en — this protocol itself — and vow, the pre-commitments that bind each engagement.
Instructions file
Instructions for rlaope/nen, covering claude.md, what this repo is — and is not, source of truth and generated files, the skill contract (enforced by scripts/lint-skills.py) and gates — run before every commit.
Skill Claude CodeCodex
Failure-mode-driven reliability engineering — enumerate how it breaks, give every mode a verdict, prove every handler with a reproducing test. Use when the user says "flaky", "harden this before launch", "what if this fails", "error handling", "timeout", "retry", "idempotency", or "race condition"; when an incident or…
Skill Claude CodeCodex
Launch, positioning, and promotion — making finished work land with the audience that should care. Use when the user says "launch", "announce", "release notes", "changelog", "blog post", "tweet thread", "X thread", "Show HN", "Hacker News post", "how do I promote this", "who would care about this", or "positioning"…
Skill Claude CodeCodex
Aura-field auto-routing — read an incoming request's problem shape and engage the right nen abilities, stacked in dependency order when the work spans more than one discipline. Use when the user says "nen", "use nen", "nen mode", "run this through nen", "which skill applies", or "route this"; when a request plausibly…
Skill Claude CodeCodex
Profiling-first performance engineering — baseline, profile, change one thing, re-measure. Use when the user says "slow", "make this faster", "optimize", "profile", "benchmark", or "hot path"; when they report latency problems, p99 spikes, low throughput, memory growth, or N+1 queries; when a request times out under…
Skill Claude CodeCodex
Skill forging — distilling a team's recurring, hard-won practice into a new installable SKILL.md that meets the nen contract. Use when the user says "write a skill", "create a skill for", "turn this workflow into a skill", "codify our process", or "SKILL.md"; when someone says "we keep solving this the same way" or…
Skill Claude CodeCodex
Orchestration engineering for multi-agent and deep-research work — decomposition, routing, prompt design, and verified delegation. Use when the user says "plan this", "break this down", "delegate", "orchestrate", "subagent", "task distribution", "parallel workstreams", "split this across agents", "hand this to three…
Skill Claude CodeCodex
Reverse engineering and mechanism-comparison research — when the docs run out, read the artifact itself and prove how the thing actually works. Use when the user asks "how does actually do it", says "reverse engineer this", "undocumented behavior", "the docs don't match what happens", or "the docs never mention it"…
Skill Claude CodeCodex
Behavior-preserving refactoring under characterization tests, plus severity-rated code review. Use when the user says "refactor", "clean up", "tech debt", "code review", "extract", "rename", "restructure", "this file is a mess", or "impossible to modify"; when every small change breaks something unrelated; when…
Skill Claude CodeCodex
Pre-commitment engineering — declare falsifiable vows before the work starts and audit every one before claiming done, discipline pledges distilled from the engaged skills' Done means plus scope pledges bounding the blast radius. Use when the user says "don't touch anything else", "only this file", "stay in scope"…
Plugin Claude Code
Plugin marketplace listing 1 plugin: claude-code-savant.
Plugin Claude Code
5 core personas, 16 dev specialist agents (language optimizers, infra/DevOps, SRE), and 14 business domain agents with distinctive character and expertise.
MCP server Claude CodeCodexCursor
MCP server "claude-code-savant" as configured in rlaope/claude-code-savant. Runs dist/index.js with node.
Instructions file
Claude Code instructions for rlaope/claude-code-savant, covering claude code savant - development rules, project overview, agent categories, key files and git workflow.
Agent
You are the Router, an expert at analyzing questions and determining which Savant persona would provide the best response. Your job is to classify questions with high accuracy and explain your reasoning.
Command
Disable Savant default mode - return to normal Claude behavior.
Command
Enable Savant as default mode - auto-routes all questions to the best persona.
Command
Auto-runs on first install - Savant setup wizard.
Command
Change Savant response language (English, Korean, Japanese, Chinese).
Command
Manage which dev specialist and biz agents are active.
Command
AWS cloud architecture with AWS Architect agent.
Command
Launch Savant Chat - web messenger UI to chat with AI personas about your project.
Command
CI/CD pipeline design with CI/CD Engineer agent.