Instructions file CodexOpenCode
Instructions for MatthewYe/opencode-toolbox, covering opencode-toolbox, quick start, architecture, upstream skills (git subtree) and autopilot workflow.
5 2mo ago A 1,096 tokens
original MIT
argus
02Agent
A specialised helper for analysing images and other visual input, with reports written in Chinese.
5 2mo ago A 29 tokens
original MIT
implementer
03Agent
An autonomous implementation agent that follows an AGENT-BRIEF, a written task contract, and uses TDD, or test-driven development, while coding. It also diagnoses unexpected errors and adjusts its approach.
5 2mo ago A 32 tokens
original MIT
reviewer
04Agent
A read-only reviewer for autopilot coding tasks. It checks whether the implementation matches the plan, tests follow TDD (test-driven development) practices, the code is sound, and related modules remain consistent.
5 2mo ago A 39 tokens
original MIT
Command
Post-hoc audit of autopilot execution fidelity. Analyzes session traces from an /autopilot run to evaluate how faithfully the workflow executed against its contract, surfacing errors, friction, and drift with traceable evidence anchors.
5 2mo ago A 47 tokens
original MIT
autopilot
06Command
Put issue resolution on autopilot — scans local .scratch/ files AND GitHub Issues for ready-for-agent issues, dispatches implementer → reviewer in a retry loop until resolved. After all issues complete, runs global meta-review against ADR/PRD and fixes cross-module issues. Use when processing autopilot issues from any…
5 2mo ago A 66 tokens
original MIT
Command
Set up git guardrails in OpenCode — adds permission rules to block dangerous git commands (push, reset --hard, clean, branch -D, checkout/restore .) before they execute. Use to prevent destructive git operations.
5 2mo ago A 46 tokens
original MIT
Command
Create, modify, and improve agent skills with iterative eval-driven development.
5 2mo ago A 14 tokens
original MIT
teach
09Command
Teach the user a new skill or concept over multiple sessions, using the current directory as a stateful teaching workspace.
5 2mo ago A 23 tokens
original MIT
domain
10Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
5 2mo ago A 0 tokens
copy · 84% MIT
Agent
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
5 2mo ago A 0 tokens
copy · 83% MIT
Agent
A review checklist for an agent that checks another agent’s software work against requirements, tests, project rules, and related modules.
5 2mo ago A 0 tokens
original MIT
Agent
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
5 2mo ago A 0 tokens
copy · 75% MIT
Skill Claude CodeCodex
Post-hoc audit of autopilot execution fidelity. Analyzes OpenCode session traces to evaluate how faithfully the autopilot workflow executed against its contract, surfacing errors, friction, and drift with traceable evidence anchors. Use when the user wants to audit an autopilot run, analyze session quality, check if…
5 2mo ago A 87 tokens
original MIT
Skill Claude CodeCodex
Set up OpenCode permission rules to guard against dangerous git commands (push, reset --hard, clean, branch -D, checkout/restore .) before they execute. Use when user wants to prevent destructive git operations, add git safety guardrails, or block dangerous git commands.
5 2mo ago A 61 tokens
original MIT
Skill Claude CodeCodex
Create OpenCode plugin scaffolding from scratch or fix existing projects to conform to plugin conventions. Supports npm packages (publishable) and local auto-discovered plugins. Use when the user wants to create a new opencode plugin, scaffold a plugin project, fix/align an existing plugin project, or mentions plugin…
5 2mo ago A 79 tokens
original MIT
Skill Claude CodeCodex
Create, modify, and improve agent skills with iterative eval-driven development. Use when user wants to create a new skill from scratch, edit or optimize an existing skill, run evals to test skill performance, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering…
5 2mo ago A 63 tokens
original MIT
analyzer
18Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
5 2mo ago A 0 tokens
original MIT
comparator
19Agent
Compare two outputs WITHOUT knowing which skill produced them.
5 2mo ago A 0 tokens
original MIT
grader
20Agent
Evaluate expectations against an execution transcript and outputs.
5 2mo ago A 0 tokens
copy · 73% MIT
Skill Claude CodeCodex
AFK agent cluster for opencode — implementer, reviewer, TDD/discipline skills, installable via symlinks.
5 2mo ago A 4 tokens
original MIT
empty-skill
22Skill Claude CodeCodex
AFK agent cluster for opencode — implementer, reviewer, TDD/discipline skills, installable via symlinks.
5 2mo ago A 3 tokens
original MIT
Skill Claude CodeCodex
AFK agent cluster for opencode — implementer, reviewer, TDD/discipline skills, installable via symlinks.
5 2mo ago A 0 tokens
original MIT
test-skill
24Skill Claude CodeCodex
A test skill.
5 2mo ago A 7 tokens
original MIT