skills/ellamaka-config/SKILL.md
Configure ellamaka, a fork of OpenCode with wopal-space mode. MUST use for any task about ellamaka config, agent frontmatter, permission rules, model/provider selection, formatter settings, config loading order, or why config changes are ignored. Trigger on requests about ellamaka or opencode config files, agent permission overrides, restricting subagents, custom/plugin tool permissions (e.g. wopal_task_*), disabling tools, configuring providers or models, formatter setup, config precedence or layering, or debugging settings that do not take effect. Use this skill even when the user says "opencode" if the actual runtime, config path, or behavior is ellamaka. Prefer this skill whenever the answer depends on the difference between ellamaka and upstream opencode, including wopal-space config loading, plugin tool permissions, or agent frontmatter precedence.
npx skillsauth add sampx/agent-tools ellamaka-configInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Configure and troubleshoot ellamaka, a fork of OpenCode with wopal-space mode and plugin tool support.
Check this first, because the validation path changes everything.
opencodeellamaka CLI directlyWhy: ellamaka is a fork with wopal-space-specific config loading and plugin tools.
| Type | Path |
|------|------|
| Global config | ~/.wopal/ellamaka/config/opencode.jsonc |
| Project config | opencode.jsonc in project root |
| Global agents | ~/.wopal/agents/{name}.md |
When running inside a WopalSpace, an extra space-local config layer is inserted:
| Type | Path |
|------|------|
| Space config | <space-root>/.wopal/config/settings.jsonc under ellamaka key |
| Space agents | <space-root>/.wopal/agents/{name}.md |
~/.wopal/ellamaka/config/opencode.jsonc (global).wopal/config/settings.jsonc → ellamaka key.wopal/agents/{name}.md frontmatteropencode.jsonc (generic mode only)Important wopal-space differences:
opencode.jsonc~/.config/opencode/Use permission, not legacy tools, for new config.
{
"permission": {
"edit": "allow",
"bash": {
"*": "ask",
"git *": "allow",
"rm *": "deny"
}
}
}
Prefer agent frontmatter for subagent boundaries:
---
permission:
wopal_*: deny
skill:
"*": deny
df-implement-review: allow
todowrite: allow
---
ellamaka permission rules support custom tool names, not only built-in tools:
permission:
wopal_task: deny
wopal_task_output: deny
wopal_*: deny
Use wildcard rules when you want one boundary for a whole plugin tool family.
~/.wopal/ellamaka/config/opencode.jsonc.wopal/config/settings.jsonc under ellamakaellamaka.agent.<name> (WopalSpace) or agent.<name> (generic)Example (WopalSpace):
{
"ellamaka": {
"agent": {
"rook": {
"model": "github-copilot/gpt-5.4"
}
}
}
}
Use agent frontmatter when the rule belongs to one agent's role.
Typical cases:
skill visibilityCheck in this order:
ellamaka, not opencode?After config edits, validate with ellamaka itself.
ellamaka run "test"
Check resolved agent permissions:
ellamaka agent list
Use ellamaka agent list after permission edits to confirm the resolved rules actually include your new entries.
references/config-schema.md — schema reference (in this skill directory)| Problem | Check |
|---|---|
| Config not taking effect | You may be editing the wrong layer; check frontmatter > space config > global |
| Works in opencode but not ellamaka | Wrong runtime; validate with ellamaka directly |
| Permission change seems ignored | Confirm with ellamaka agent list |
| Custom tool rule not matching | Use exact tool name or wildcard like wopal_* |
| Legacy config found | Migrate tools → permission, maxSteps → steps |
development
Plan quality verification for dev-flow. Goal-backward analysis ensures plans WILL achieve their stated goal before execution burns context. ⚠️ MUST use when: (1) Reviewing Plan quality before approve (2) Wopal completes Plan writing and needs quality gate (3) User asks to "check plan", "verify plan", "review plan" (4) Plan enters planning status and needs pre-execution validation 🔴 Trigger automatically when Plan is ready for review, even if user doesn't explicitly say "review". Agent: rook (read-only verification subagent) Mode: verification, not execution
development
Review implementation results for goal achievement and code quality. Supports both Plan-backed review and planless diff review. ⚠️ MUST use when: (1) Wopal delegates rook to review fae implementation output, (2) Prompt contains "review_type: implementation", (3) Prompt contains changed code file list or Plan path + implementation scope, (4) Any code review request from Wopal. 🔴 Trigger even when user does not explicitly mention "review" if the task involves verifying implementation results. This skill is rook-exclusive (only rook agent can load it).
tools
Foundation rules for how Wopal collaborates with sub-agents such as fae and rook. ⚠️ MUST load before ANY delegation — covers delegation tool APIs, task lifecycle, notifications, status handling, and recovery. 🔴 Trigger: "delegate", "let fae implement", "fae task", "rook review", "check task status", "cancel task", "abort task", "agent collaboration", "委派", "让 fae 执行", "fae 任务", "rook 审查", "检查状态", or any intent to hand work to a sub-agent. 🔴 Never delegate without loading this skill first. Skipping it is serious negligence. Note: this skill does not include workflow-specific prompt templates such as dev-flow templates. Those belong to the corresponding workflow skills.
tools
Manage parallel workstreams — list, create, switch, status, progress, complete, and resume