Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/humanerd-drew/opencode-drewgent/agents-mdgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01826 | $0.01826 |
| Opus 5 | $0.00913 | $0.00913 |
| Sonnet 5 | $0.00365 | $0.00365 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
opencode-drewgent AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
opencode-drewgent — Agent Template Guide
This is a template — a starting point for your own personal AI agent system. Fork it, rename it, and make it yours.
Architecture Overview
opencode-drewgent provides a structured agent system built on opencode. It includes:
- Subagent profiles — specialized agent roles (engineer, reviewer, analyst, etc.) with assigned models and tool permissions
- Delegation patterns —
task()for same-model subtasks,gjc_delegate_*for isolated/parallel execution via GJC Coordinator MCP - Vault structure — P0-P6 Obsidian vault for rules, identity, memory, sensors, cortex, ego, and prefrontal
- MCP integration — example config for local and remote MCP servers
- Kanban pipeline — task decomposition with leverage scoring
- Cron automation — example jobs for housekeeping, content, and monitoring
Structure Principles
.
├── agent/ ← Core .py package (NOT root-level .py files)
├── gateway/ ← Platform adapters
├── cron/ ← Scheduler
├── tools/ ← Tool implementations
├── skills/ ← Agent skills
├── projects/ ← External work (one subdir per project)
├── brain/ ← P0-P6 vault + @identity
├── state/ ← DBs, logs, sessions
├── config/ ← Settings, dotfiles
└── docs/ ← Documentation
Key rule: Root must stay lean. Agent code goes in agent/. External work goes in projects/. Flat root accumulation is tech debt — each file at root is a decision that needs a justification.
Subagent Profiles
See .opencode/agents/*.md for the full list. Key profiles:
| Profile | Model | Role |
|---|---|---|
| implementer | flash | Code generation, file edits |
| reviewer | pro | Code review, quality gate |
| explorer | flash | Codebase discovery, research |
| planner | max | Task decomposition, planning |
| architect | pro | Architecture decisions |
| sre | flash | Infrastructure, monitoring |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 197 lines · 1,826 tokens per session scan A df9c6304cce4
opencode-drewgent AGENTS.md is an instructions file published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,826 tokens to every session, about $0.0091 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
open-supermarkets AGENTS.md
Instructions for abracadabra50/open-supermarkets, covering agent integration guide, supported frameworks, quick integration, 1. add as skill and 2. agent calls commands.
helm copilot-instructions.md
Instructions for PetePeter/helm, covering gamepad-cli-hub — copilot instructions, project purpose, system overview, data flow pipeline and key controls.
fusion-skills AGENTS.md
AGENTS.md instructions for CrowdStrike/fusion-skills, covering agents.md, what this is, prerequisites, repository structure and skills ecosystem.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.