chore: update opencode workflow and local config

.config/opencode/skills/creating-agents/SKILL.md

@@ -0,0 +1,66 @@
+---
+name: creating-agents
+description: Create or update opencode agents in this repository, including dispatch permissions and roster alignment requirements
+permalink: opencode-config/skills/creating-agents/skill
+---
+
+# Creating Agents
+
+Use this skill when you need to add or revise an agent definition in this repo.
+
+## Agents vs Skills
+
+- **Agents** define runtime behavior and permissions in `agents/*.md`.
+- **Skills** are reusable instruction modules under `skills/*/SKILL.md`.
+- Do not treat agent creation as skill creation; each has different files and checks.
+
+## Source of Truth
+
+1. Agent definition file: `agents/<agent-name>.md`
+2. Dispatch permissions for new dispatchable agents: `agents/lead.md`
+   - `permission.task.<agent-name>: allow` must be present for lead dispatch.
+3. Human-readable roster: `AGENTS.md`
+   - Keep the roster table synchronized with actual agent files.
+4. Runtime overrides: `opencode.jsonc`
+   - May override/disable agent behavior.
+   - Does **not** register a new agent.
+
+## Agent File Conventions
+
+For `agents/<agent-name>.md`:
+
+- Use frontmatter first, then concise role instructions.
+- Keep tone imperative and operational.
+- Include only permissions and behavior needed for the role.
+- Align with existing files such as `agents/lead.md` and `agents/coder.md`.
+
+Typical frontmatter fields in this repo include:
+
+- `description`
+- `mode`
+- `model` (for subagents where needed)
+- `temperature`
+- `permission`
+- `permalink`
+
+ Mirror nearby agent files instead of inventing new metadata patterns.
+ Note: `agents/lead.md` is the only `mode: primary` agent. New agents should normally mirror a comparable subagent and use `mode: subagent` with an explicit `model`.
+
+## Practical Workflow (Create or Update)
+
+1. Inspect `agents/lead.md` and at least one similar `agents/*.md` file.
+2. Create or edit `agents/<agent-name>.md` with matching local structure.
+3. If the agent must be dispatchable, add `permission.task.<agent-name>: allow` in `agents/lead.md`.
+4. Update `AGENTS.md` roster entry to match the new/updated agent.
+5. Review `opencode.jsonc` for conflicting overrides/disable flags.
+
+## Manual Verification Checklist (No Validation Script)
+
+Run this checklist before claiming completion:
+
+- [ ] `agents/<agent-name>.md` exists and frontmatter is valid/consistent with peers.
+- [ ] Agent instructions clearly define role, scope, and constraints.
+- [ ] `agents/lead.md` includes `permission.task.<agent-name>: allow` if dispatch is required.
+- [ ] `AGENTS.md` roster row exists and matches agent name/role/model.
+- [ ] `opencode.jsonc` does not unintentionally disable or override the new agent.
+- [ ] Terminology stays consistent: agents in `agents/*.md`, skills in `skills/*/SKILL.md`.

.config/opencode/skills/creating-skills/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: creating-skills
+description: Create or update opencode skills in this repository using the required SKILL.md format and concise, trigger-focused guidance
+permalink: opencode-config/skills/creating-skills/skill
+---
+
+# Creating Skills
+
+Use this skill when you need to add or revise an opencode skill under `skills/`.
+
+## Skills vs OpenAI/Codex Source Model
+
+- Treat this repo as **opencode-native**.
+- Do **not** use OpenAI/Codex-specific artifacts such as `agents/openai.yaml`, `init_skill.py`, `quick_validate.py`, or `scripts/references/assets` conventions from the old source model.
+- A skill is discovered from `skills/*/SKILL.md` only.
+
+## Required Structure
+
+1. Create a folder at `skills/<skill-name>/`.
+2. Add `skills/<skill-name>/SKILL.md`.
+3. Keep `<skill-name>` equal to frontmatter `name`.
+
+Frontmatter must contain only:
+
+```yaml
+---
+name: <skill-name>
+description: <what it does and when to load>
+permalink: opencode-config/skills/<skill-name>/skill
+---
+```
+
+## Naming Rules
+
+- Use lowercase kebab-case.
+- Keep names short and action-oriented.
+- Match folder name and `name` exactly.
+
+## Body Writing Rules
+
+- Write concise, imperative instructions.
+- Lead with when to load and the core workflow.
+- Prefer short checklists over long prose.
+- Include only repo-relevant guidance.
+
+## Companion Notes (`*.md` in skill folder)
+
+Add companion markdown files only when detail would bloat `SKILL.md` (examples, deep procedures, edge-case references).
+
+- Keep `SKILL.md` as the operational entrypoint.
+- Link companion files directly from `SKILL.md` with clear “when to read” guidance.
+- Do not create extra docs by default.
+
+## Practical Workflow (Create or Update)
+
+1. Inspect 2–3 nearby skills for local style and brevity.
+2. Pick/update `<skill-name>` and folder path under `skills/`.
+3. Write or revise `SKILL.md` frontmatter (`name`, `description`, `permalink` only).
+4. Draft concise body sections: purpose, load conditions, workflow, red flags/checks.
+5. Add minimal companion `.md` files only if needed; link them from `SKILL.md`.
+6. Verify discovery path and naming consistency:
+   - file exists at `skills/<name>/SKILL.md`
+   - folder name == frontmatter `name`
+   - no OpenAI/Codex-only artifacts introduced