summaryrefslogtreecommitdiff
path: root/.opencode/plugins
diff options
context:
space:
mode:
authorJesse Vincent <jesse@fsck.com>2026-10-22 21:04:25 +0000
committerJesse Vincent <jesse@fsck.com>2026-10-22 21:04:25 +0000
commit8f4b3dbd2f5ef8163e4daed5ca43a4cf08eb5d8c (patch)
tree0f65e906e767b7b26f110b0630415f6c3e409f43 /.opencode/plugins
parent0f9581f6c1525b51dc1600b14d24f3db1f601446 (diff)
fix(opencode): tell the model skill ids are bare names (#2583)fix/2583-opencode-skill-names
Skills name each other with the Claude Code plugin namespace (`superpowers:brainstorming`), and the using-superpowers bootstrap that the OpenCode plugin injects says "Let's build X -> superpowers:brainstorming first". OpenCode registers superpowers skills under bare ids (`brainstorming`) on both flavors and its `skill` tool does an exact lookup, so a model that copies the namespaced form gets "Unable to load skill superpowers:brainstorming" (V2) or `Skill "superpowers:brainstorming" not found` (V1) and carries on without the skill. The OpenCode tool mapping said only "Invoke a skill -> OpenCode's native skill tool" and never stated the id convention. Reproduced on real hosts (OpenCode 2.1.2 and opencode-ai 1.19.4) with a scripted stub provider: the namespaced call fails, the bare id loads. Add the convention to the "Invoke a skill" line of both mappings, with each flavor's real skill parameter (V1 `name`, V2 `id`), and mirror it in docs/README.opencode.md. Skill prose keeps the prefix, which is correct on Claude Code; the translation belongs in the harness mapping, the same way the Hermes reference shows bare `skill_view("brainstorming")`. Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
Diffstat (limited to '.opencode/plugins')
-rw-r--r--.opencode/plugins/superpowers.js4
1 files changed, 2 insertions, 2 deletions
diff --git a/.opencode/plugins/superpowers.js b/.opencode/plugins/superpowers.js
index 9eff811..8d508db 100644
--- a/.opencode/plugins/superpowers.js
+++ b/.opencode/plugins/superpowers.js
@@ -78,7 +78,7 @@ export const V1_MAPPING = `**Tool Mapping for OpenCode:**
When skills request actions, substitute OpenCode equivalents:
- Create or update todos → \`todowrite\`
- \`Subagent (general-purpose):\` → \`task\` with \`subagent_type: "general"\`
-- Invoke a skill → OpenCode's native \`skill\` tool
+- Invoke a skill → OpenCode's native \`skill\` tool. Skill ids are bare names, so drop the \`superpowers:\` prefix skills use when they name each other (\`superpowers:brainstorming\` → \`skill\` with \`name: "brainstorming"\`)
- Read files → \`read\`
- Create, edit, or delete files → \`apply_patch\`
- Run shell commands → \`bash\`
@@ -96,7 +96,7 @@ export const V2_MAPPING = `**Tool Mapping for OpenCode:**
When skills request actions, substitute OpenCode equivalents:
- Create or update todos → OpenCode v2 has no todo tool; track the plan in a markdown file (or the harness's plan facility) instead
- \`Subagent (general-purpose):\` → \`subagent\` with \`agent: "general"\` (give it \`description\` and \`prompt\`, optionally \`background\`; pass \`sessionID\` to continue a previous subagent)
-- Invoke a skill → OpenCode's native \`skill\` tool
+- Invoke a skill → OpenCode's native \`skill\` tool. Skill ids are bare names, so drop the \`superpowers:\` prefix skills use when they name each other (\`superpowers:brainstorming\` → \`skill\` with \`id: "brainstorming"\`)
- Read files → \`read\`
- Create, edit, or delete files → use \`patch\` with \`patchText\` when available; otherwise use \`write\` to create or overwrite files, \`edit\` for targeted changes, and \`shell\` for deletion
- Run shell commands → \`shell\` (\`command\`, \`workdir\`, \`timeout\`, \`background\`)