humanerd-drew/opencode-drewgent

Drewgent configuration for opencode — agent profiles, skills, scripts, and tooling

This repository also configures its own agents. See what opencode-drewgent tells them →

3Stars on the repository
162Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

brain-signal-system

01

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

Date: 2026-05-31 (updated 2026-06-11) Status: Operational Source: agent/brainsignals.py, agent/signalprocessor.py, agent/eventbus.py, agent/awarenessreporter.py, agent/brainmonitor.py Purpose: Single source of truth for {{AGENTNAME}}'s brain signal architecture.

not rated 3 3mo ago A 0 tokens original MIT

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

A development guide for building an AI agent that can split difficult tasks into smaller tasks, run them through child agents, and combine their results. It uses test-driven development (TDD), meaning tests are written and checked as the system is built.

not rated 3 3mo ago A 57 tokens original MIT

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

Integrate {{AGENTNAME}} with ACP (Agent Client Protocol) agents. Reverse-engineered from goose's Rust ACP provider implementation.

not rated 3 3mo ago A 34 tokens original MIT

vault-health

04

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

Maintain .{{AGENTNAMELOWER}} as an Obsidian vault — graph connectivity overhaul (P-layer mesh, skill clusters, SEO article web), broken link detection, backlink density verification via Obsidian CLI, filename deduplication, bidirectional linking, auto-generated orphan management, cron output graph bloat prevention…

not rated 3 3mo ago A 74 tokens original MIT

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

A monitoring system for an AI agent's stored rules and internal state, called a brain dashboard. It includes scripts for text-based and web dashboards, rule monitoring, session-end processing, scheduled growth reports, and Discord alerts.

not rated 3 3mo ago A 0 tokens original MIT

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex needs its repo

Sync trend-harvester analyzed output to P2-hippocampus memories — bidirectional bridge between P4-cortex growth engine and P2-hippocampus long-term memory.

not rated 3 3mo ago A 0 tokens original MIT

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

A step-by-step guide for adding a new external tool to an AI agent's tool registry. It covers the handler, the model's tool list, and the toolset assignment.

not rated 3 3mo ago A 0 tokens original MIT

harsh-critic

08

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

Skill "harsh-critic" from humanerd-drew/opencode-drewgent, covering harsh critic — completion bias defense, purpose, 3-tier classification, extreme — hard block (exit 2) and high — fail + mandatory fix.

not rated 3 3mo ago A 0 tokens original MIT

qa-cycle

09

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

Contract-First QA pipeline - implements 3-phase QA (contract → micro-QA → full-QA) using P2-hippocampus qa-evidence system.

not rated 3 3mo ago A 34 tokens original MIT

semblent-search

11

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

Semantic code search using Semble — find code by intent rather than exact matches. Use when exploring unfamiliar codebases or searching for patterns that are hard to express as regex.

not rated 3 3mo ago A 0 tokens original MIT

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

A session note tool that records Discord conversations in Obsidian, a Markdown-based note-taking app, when threads end or become inactive. It captures intentions, reasoning, decisions, blind spots, and follow-up tasks.

not rated 3 3mo ago A 0 tokens original MIT

skill-gym

13

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

A weekly self-review system for an agent's skills. It finds skills that have not been used recently, scores their relevance and novelty, and produces a Discord report with recommendations and possible removal candidates.

not rated 3 3mo ago B 0 tokens original MIT

trend-harvester

14

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

AI Trend Collection & Filtering — collect GitHub trending repos, score via 5-axis philosophy filter, evaluate, apply, and retire.

not rated 3 3mo ago A 32 tokens original MIT

agent-profiles

15

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

Authoring and using agent profiles — pre-defined subagent roles that set model, provider, toolsets, and instructions in one task() call. Covers profile format, the 14 standard roles, pipeline patterns, cost-tiered model assignment, and the ESCALATE mechanism for capability routing.

not rated 3 3mo ago A 0 tokens original MIT

macos-computer-use

16

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

Drive the macOS desktop in the background — screenshots, mouse, keyboard, scroll, drag — without stealing the user's cursor, keyboard focus, or Space. Works with any tool-capable model. Load this skill whenever the computeruse tool is available.

not rated 3 3mo ago A ✓ AI review 60 tokens copy · 89% MIT

n8n-password-reset

17

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

A procedure for resetting an n8n account password by changing its stored password hash in n8n’s SQLite database. SQLite is a small file-based database used here by n8n.

not rated 3 3mo ago A 0 tokens original MIT

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

A guide for diagnosing and managing a self-hosted n8n installation on macOS. n8n is a tool for connecting services and automating workflows; self-hosted means it runs on your own computer or server.

not rated 3 3mo ago B 0 tokens original MIT

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

Add a "Thinking..." spinner card to an ACP server's tool-call stack so ACP clients (Zed Agent Panel, openCode TUI, JetBrains/VS Code ACP UI) show a working indicator during the LLM API call phase. Triggers when working on an Agent Client Protocol (ACP) server and the user wants LLM-thinking visibility in the client's…

not rated 3 3mo ago A 82 tokens original MIT

content-management

20

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

CMO-style autonomous content agent. Observes user's work activity (sessions, git, kanban), curates narrative-worthy material, produces multi-format drafts (blog + X thread), maintains narrative arc continuity, and generates visual assets (SVG cover, Mermaid, Excalidraw PNG). session: "2026-06-14…

not rated 3 3mo ago A 127 tokens original MIT

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

Complete guide to using and extending {{AGENTNAME}} Agent — CLI usage, setup, configuration, spawning additional agents, gateway platforms, skills, voice, tools, profiles, and a concise contributor reference. Load this skill when helping users configure {{AGENTNAME}}, troubleshoot issues, spawn agent instances, or…

not rated 3 3mo ago C 0 tokens original MIT

daily-retro

22

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

A daily review workflow that summarizes your work, sends reflection questions through Discord, and saves your answers in a structured vault. Discord is a chat app, and a vault is a folder of organized notes.

not rated 3 3mo ago A 0 tokens original MIT

humanerd-drew/opencode-drewgent

Skill Claude CodeCodex

A hardening change for a Kanban task dispatcher, which assigns work from a queue to workers. It checks whether workers are still running and reclaims tasks from dead workers within the correct board.

not rated 3 3mo ago A 0 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: