naimkatiman/continuous-improvement
Plugin Claude Code
Marketplace for the Continuous Improvement Claude Code plugin and four vendored upstream companions (Obra superpowers, addyosmani/agent-skills, ruflo-swarm, oh-my-claudecode). All four companions are pinned-SHA snapshots in third-party/ — see third-party/MANIFEST.md for refresh recipes and per-snapshot OURNOTES.md for.
naimkatiman/continuous-improvement
MCP server Claude CodeCodexCursor +2
MCP server "continuous-improvement-dev" as configured in naimkatiman/continuous-improvement. Runs ./bin/mcp-server.mjs with node.
naimkatiman/continuous-improvement
Instructions file CodexOpenCode
Instructions for naimkatiman/continuous-improvement, covering agents.md — continuous-improvement, repository, think before acting, verification discipline and build pipeline (critical).
naimkatiman/continuous-improvement
Instructions file
Instructions for naimkatiman/continuous-improvement, covering claude.md — continuous-improvement, repository, think before acting, verification discipline and build pipeline (critical).
naimkatiman/continuous-improvement
Skill Claude CodeCodex
Install structured self-improvement loops with instinct-based learning into Claude Code — research, plan, execute, verify, reflect, learn, iterate. On-demand or weekly analysis to save tokens. Supports multi-agent parallel analysis.
naimkatiman/continuous-improvement
Agent
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
naimkatiman/continuous-improvement
Agent
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
naimkatiman/continuous-improvement
Agent
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
naimkatiman/continuous-improvement
Command
Audit a window of recent commits for real defects, confirm each finding before fixing, verify every surface a fix touches, then report confirmed/dismissed/no-op with evidence. Enforces Law 4 (Verify Before Reporting).
naimkatiman/continuous-improvement
Command
Inspect companion-preference hook telemetry — counts by CI skill, action breakdown, and companion-installed%.
naimkatiman/continuous-improvement
Command
Reflect on the current session, analyze observations for patterns, and show instinct status. Runs on-demand to save tokens.
naimkatiman/continuous-improvement
Command
Visual dashboard showing instinct health, observation stats, and learning progress.
naimkatiman/continuous-improvement
Command
Quick reference card for the 7 Laws of AI Agent Discipline.
naimkatiman/continuous-improvement
Command
Distill repeated successful tool sequences from the observation log into reusable draft instincts, with an explicit propose-edit-promote ladder. Enforces Law 7 (Learn From Every Session).
naimkatiman/continuous-improvement
Command
Check whether recent tool activity still relates to the stated goal in taskplan.md, reporting a drift score and the top off-goal tool calls. Enforces Law 2 (Plan Is Sacred).
naimkatiman/continuous-improvement
Command
Interview the user relentlessly about a plan or design until shared understanding is reached. Ported from mattpocock/skills under MIT.
naimkatiman/continuous-improvement
Command
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates CONTEXT.md + ADRs inline as decisions crystallise. Ported from mattpocock/skills under MIT.
naimkatiman/continuous-improvement
Command
Compact the current conversation into a handoff document for another agent to pick up. Ported from mattpocock/skills under MIT.
naimkatiman/continuous-improvement
Command
Harvest friction events from observation logs into typed instincts (envissue, permissionblock, wrongapproach, buggycode) with confidence scoring.
naimkatiman/continuous-improvement
Command
Turn an ambiguous or high-impact change into scoped, verifiable acceptance criteria (observable AC-NNN, explicit scope, named verification methods, and a [revised] protocol that forbids silently dropping a criterion) before or alongside implementation. Enforces Law 2 (Plan Is Sacred).
naimkatiman/continuous-improvement
Command
Extract reusable patterns from the session, self-evaluate quality before saving, and determine the right save location (Global vs Project).
naimkatiman/continuous-improvement
Command
Restate the model-forward stance — go with Claude, not against it; skills are scaffolding; the durable core is goal-driven execution plus guardrails.
naimkatiman/continuous-improvement
Command
Create and maintain taskplan.md, findings.md, and progress.md for persistent file-based planning.
naimkatiman/continuous-improvement
Command
Execute the agent's prior recommendation list under the 7 Laws — walk in order, route per item, verify, reflect. Standalone companion skill with inline fallbacks when other skills are not installed.