Reduce context token usage by 79% — fix silent component exclusion (#161)

* Update create-agent-skills to match 2026 official docs, add /triage-prs command

- Rewrite SKILL.md to document that commands and skills are now merged
- Add new frontmatter fields: disable-model-invocation, user-invocable, context, agent
- Add invocation control table and dynamic context injection docs
- Fix skill-structure.md: was incorrectly recommending XML tags over markdown headings
- Update official-spec.md with complete 2026 specification
- Add local /triage-prs command for PR triage workflow
- Add PR triage plan document

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* [2.31.0] Reduce context token usage by 79%, include recent community contributions

The plugin was consuming 316% of Claude Code's description character budget
(~50,500 chars vs 16,000 limit), causing components to be silently excluded.
Now at 65% (~10,400 chars) with all components visible.

Changes:
- Trim all 29 agent descriptions (move examples to body)
- Add disable-model-invocation to 18 manual commands
- Add disable-model-invocation to 6 manual skills
- Include recent community contributions in changelog
- Fix component counts (29 agents, 24 commands, 18 skills)

Contributors: @trevin, @terryli, @robertomello, @zacwilliams,
@aarnikoskela, @samxie, @davidalley

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Fix: keep disable-model-invocation off commands called by /lfg, rename xcode-test

- Remove disable-model-invocation from test-browser, feature-video,
  resolve_todo_parallel — these are called programmatically by /lfg and /slfg
- Rename xcode-test to test-xcode to match test-browser naming convention

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Fix: keep git-worktree skill auto-invocable (used by /workflows:work)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat(converter): support disable-model-invocation frontmatter

Parse disable-model-invocation from command and skill frontmatter.
Commands/skills with this flag are excluded from OpenCode command maps
and Codex prompt/skill generation, matching Claude Code behavior where
these components are user-only invocable.

Bump converter version to 0.3.0.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

src/converters/claude-to-codex.ts

@@ -19,7 +19,8 @@ export function convertClaudeToCodex(
 
   const usedSkillNames = new Set<string>(skillDirs.map((skill) => normalizeName(skill.name)))
   const commandSkills: CodexGeneratedSkill[] = []
-  const prompts = plugin.commands.map((command) => {
+  const invocableCommands = plugin.commands.filter((command) => !command.disableModelInvocation)
+  const prompts = invocableCommands.map((command) => {
     const promptName = uniqueName(normalizeName(command.name), promptNames)
     const commandSkill = convertCommandSkill(command, usedSkillNames)
     commandSkills.push(commandSkill)

src/converters/claude-to-opencode.ts

@@ -114,6 +114,7 @@ function convertAgent(agent: ClaudeAgent, options: ClaudeToOpenCodeOptions) {
 function convertCommands(commands: ClaudeCommand[]): Record<string, OpenCodeCommandConfig> {
   const result: Record<string, OpenCodeCommandConfig> = {}
   for (const command of commands) {
+    if (command.disableModelInvocation) continue
     const entry: OpenCodeCommandConfig = {
       description: command.description,
       template: command.body,

src/parsers/claude.ts

@@ -83,12 +83,14 @@ async function loadCommands(commandsDirs: string[]): Promise<ClaudeCommand[]> {
     const { data, body } = parseFrontmatter(raw)
     const name = (data.name as string) ?? path.basename(file, ".md")
     const allowedTools = parseAllowedTools(data["allowed-tools"])
+    const disableModelInvocation = data["disable-model-invocation"] === true ? true : undefined
     commands.push({
       name,
       description: data.description as string | undefined,
       argumentHint: data["argument-hint"] as string | undefined,
       model: data.model as string | undefined,
       allowedTools,
+      disableModelInvocation,
       body: body.trim(),
       sourcePath: file,
     })
@@ -104,9 +106,11 @@ async function loadSkills(skillsDirs: string[]): Promise<ClaudeSkill[]> {
     const raw = await readText(file)
     const { data } = parseFrontmatter(raw)
     const name = (data.name as string) ?? path.basename(path.dirname(file))
+    const disableModelInvocation = data["disable-model-invocation"] === true ? true : undefined
     skills.push({
       name,
       description: data.description as string | undefined,
+      disableModelInvocation,
       sourceDir: path.dirname(file),
       skillPath: file,
     })

src/types/claude.ts

@@ -39,6 +39,7 @@ export type ClaudeCommand = {
   argumentHint?: string
   model?: string
   allowedTools?: string[]
+  disableModelInvocation?: boolean
   body: string
   sourcePath: string
 }
@@ -46,6 +47,7 @@ export type ClaudeCommand = {
 export type ClaudeSkill = {
   name: string
   description?: string
+  disableModelInvocation?: boolean
   sourceDir: string
   skillPath: string
 }