Initialise Accelerator

You prepare a consumer repository with all directories and gitignore entries that Accelerator skills expect. This is safe to run repeatedly — it reports what was created versus what already existed.

Path Resolution

Resolve each output directory using the plugin's path configuration:

Plans directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path plans --fail-safe Research directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path research_codebase --fail-safe Decisions directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path decisions --fail-safe PRs directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path prs --fail-safe Validations directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path validations --fail-safe Review plans directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path review_plans --fail-safe Review PRs directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path review_prs --fail-safe Review work items directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path review_work --fail-safe Work items directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path work --fail-safe Notes directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path notes --fail-safe Design inventories directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path research_design_inventories --fail-safe Design gaps directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path research_design_gaps --fail-safe Global directory: !${CLAUDE_PLUGIN_ROOT}/bin/accelerator config path global --fail-safe

Steps

Execute the following steps in order, tracking what was created versus what already existed so you can present a summary at the end.

Steps 1–3: Run the init script

${CLAUDE_PLUGIN_ROOT}/bin/accelerator config init

The script creates 13 meta/ directories with .gitkeep files, creates the .accelerator/ core scaffold (.gitignore, state/, tmp/, skills/, lenses/, templates/), writes the inner tmp .gitignore, and appends the .accelerator/config.local.md rule to the root .gitignore. It is idempotent — safe to run repeatedly.

Step 4: Report results

Only after all steps above have completed successfully, present a summary:

Initialisation complete:

Directories:
  ✓ {plans directory} (created | already exists)
  ✓ {research directory} (created | already exists)
  ✓ {decisions directory} (created | already exists)
  ✓ {prs directory} (created | already exists)
  ✓ {validations directory} (created | already exists)
  ✓ {review plans directory} (created | already exists)
  ✓ {review prs directory} (created | already exists)
  ✓ {review work items directory} (created | already exists)
  ✓ {work items directory} (created | already exists)
  ✓ {notes directory} (created | already exists)
  ✓ {design inventories directory} (created | already exists)
  ✓ {design gaps directory} (created | already exists)
  ✓ {global directory} (created | already exists)

Accelerator scaffold:
  ✓ .accelerator/.gitignore (created | already exists)
  ✓ .accelerator/state/.gitkeep (created | already exists)
  ✓ .accelerator/skills/.gitkeep (created | already exists)
  ✓ .accelerator/lenses/.gitkeep (created | already exists)
  ✓ .accelerator/templates/.gitkeep (created | already exists)
  ✓ .accelerator/tmp/.gitignore (created | already exists)
  ✓ .accelerator/tmp/.gitkeep (created | already exists)

Gitignore entries:
  ✓ .accelerator/config.local.md (added | already present)

Use the actual resolved paths in the output (not the variable names).

---

/accelerator:init bootstraps a fresh repository. To upgrade an existing repository after a plugin update, use /accelerator:migrate instead — it applies ordered, idempotent migrations to bring meta/, .claude/, and .accelerator/ in line with the latest schema.