Find the best CLAUDE.md, AGENTS.md and Claude skills

naman10parikhAGENTS.md

agentgrid

naman10parikh/agentgrid/AGENTS.md

How AI coding agents (and the humans steering them) should work inside this repo. This is the agent-native operating contract for agentgrid itself. Co-evolve it over time. agentgrid is two products in one repo plus a self-improving harness: Use the right one; sub-agents research and review, the parent implements. CLI (the pub

naman10parikhCLAUDE.md

agentgrid

naman10parikh/agentgrid/CLAUDE.md

Forged from Energy via harness-forge (CP103). One repo = one recursively self-improving agent-native harness. Energy is the control center; this is a self-contained flavor.

naman10parikhSkill

agentgrid-orchestrate

naman10parikh/agentgrid/.claude/skills/agentgrid-orchestrate/SKILL.md

Orchestrate missions across a running agentgrid — inject tasks, broadcast to all panes, monitor live status, and read pane output. Use after a grid is already running (post agentgrid NxM). Triggers on "send mission", "broadcast", "inject", "monitor panes", "read pane output".

naman10parikhSkill

agentgrid-sessions

naman10parikh/agentgrid/.claude/skills/agentgrid-sessions/SKILL.md

Save, restore, and manage agentgrid sessions and presets — persist grid layouts, replay company configurations, and use built-in presets. Use when "save grid", "restore session", "load preset", "replay company" is needed.

naman10parikhSkill

agentgrid

naman10parikh/agentgrid/.claude/skills/agentgrid/SKILL.md

Spawn a grid of AI coding agents in one command. Use when the user wants to create parallel agent sessions, set up multi-agent terminal layouts, or launch a team of AI workers across tmux panes.

naman10parikhSkill

agent-runtime

naman10parikh/agentgrid/.claude/skills/agent-runtime/SKILL.md

Build the Energy agent runtime adapter wrapping Claude Agent SDK. This is the core of Phase 1. The adapter has TWO processes: Runs on the server. Routes messages, manages sessions, spawns sandboxes. Runs inside E2B sandbox. Calls Claude Agent SDK, executes tools.

naman10parikhSkill

frontend-design

naman10parikh/agentgrid/.claude/skills/anthropic-frontend-design/SKILL.md

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Often used withfile-reading·brief-to-tasks·instantly-campaign

naman10parikhSkill

architect

naman10parikh/agentgrid/.claude/skills/architect/SKILL.md

Use when making architectural decisions for the Energy/NRG platform. Loads architecture from VISION.md and debates trade-offs using Socratic thinking.

Often used withpoteto-help·principle-explain-the-number·make-bot-ui

naman10parikhSkill

deep-think

naman10parikh/agentgrid/.claude/skills/deep-think/SKILL.md

Activate multi-modal thinking for complex decisions. Combines Socratic thinking, self-critique, second/third-order effects, and adversarial debate.

naman10parikhSkill

design-systems

naman10parikh/agentgrid/.claude/skills/design-systems/SKILL.md

V3 design harness — discovery brief gate, DFS pipeline, 12-dimension binary audit, OKLCH colors, jakub.kr micro-details. Produces world-class designs for any vertical.

naman10parikhSkill

harness-review

naman10parikh/agentgrid/.claude/skills/harness-review/SKILL.md

Review an agent's harness (scaffold) for quality, token efficiency, and correctness. Based on harness engineering research.

naman10parikhSkill

heartbeat

naman10parikh/agentgrid/.claude/skills/heartbeat/SKILL.md

Implement the HEARTBEAT.md pattern for proactive agent behavior. Agents check for updates, run scheduled tasks, and act without user prompting. Each agent has a HEARTBEAT.md file that defines scheduled tasks: If HEARTBEAT.md is empty or missing, no heartbeat fires (saves API costs).

naman10parikhSkill

integrate-resources

naman10parikh/agentgrid/.claude/skills/integrate-resources/SKILL.md

Process new resources dropped into resources/unread/. Extracts Claude Code tips, tools, patterns and updates the setup guide, skills, hooks, and knowledge catalog.

naman10parikhSkill

llm-council-critique

naman10parikh/agentgrid/.claude/skills/llm-council-critique/SKILL.md

Run a 6-hat brutal LLM Council self-critique on any deliverable, session output, or status update. Surfaces what's actually missing, where the work is shallow, and what was tabled-for-later. Use BEFORE re-attacking a problem the maintainer has flagged twice. Encodes the Karpathy LLM Council pattern from CP82 ralph loop iterations 2 and 3 — applying the council BEFORE the next attack saves three iterations.

naman10parikhSkill

loop-create

naman10parikh/agentgrid/.claude/skills/loop-create/SKILL.md

Scaffold a new agent with the full file structure. Use when creating any new agent for the Energy platform. NOTE — ".loop" is a working name for the agent file format. When building, use a configurable extension constant.

naman10parikhSkill

memory-compression

naman10parikh/agentgrid/.claude/skills/memory-compression/SKILL.md

Production memory management for Energy agents. Prevents context loss, enables compound memory. Plain Markdown beats vector databases: 74% accuracy (ClaWHow) vs 68.5% (vector DBs). Structure IS the retrieval mechanism. OpenClaw's formula: threshold = contextWindow - reserveFloor - softThreshold Each compaction MERGES into this anchor rather than starting fresh. Factory tested this on 36,000 sessions: 4.04 accuracy vs 3.74 for alternatives. Three-stage pipeline from arXiv 2601.02553: Results: ~17K → ~550 tokens per query (97% compression). F1: 43.24%. From OpenClaw's production implementation:

naman10parikhSkill

memory

naman10parikh/agentgrid/.claude/skills/memory/SKILL.md

Search, store, compress, and recall memories across the Energy platform. Semantic search over LEARNINGS.md, daily logs, vault notes, and rules.

naman10parikhSkill

model-routing

naman10parikh/agentgrid/.claude/skills/model-routing/SKILL.md

Adaptive budget-aware model routing. Manages 4-tier system to maximize $200/mo Max plan usage across full weekly cycle. Run when starting sessions, hitting usage warnings, or optimizing sub-agent costs.

naman10parikhSkill

oss-project-scaffold

naman10parikh/agentgrid/.claude/skills/oss-project-scaffold/SKILL.md

Scaffold a new OSS CLI project with package.json, tsconfig, README template, Vitest, CI, and LICENSE. The standardized starting point for all Energy OSS tools.

naman10parikhSkill

playwright-cli

naman10parikh/agentgrid/.claude/skills/playwright-cli/SKILL.md

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Often used withfabric-sdk·schema-discovery·app-validation