Documentation Index
Fetch the complete documentation index at: https://docs.selftune.dev/llms.txt
Use this file to discover all available pages before exploring further.
Usage
selftune run in normal product guidance; selftune orchestrate remains the
backing runtime and advanced alias for the same operation.
Options
| Flag | Description |
|---|---|
--dry-run | Show what would happen without executing |
--review-required | Require human review before deploying evolutions |
--auto-approve | Deprecated alias. Autonomous deploy is already the default behavior. |
--skill NAME | Only process a specific skill |
--max-skills N | Maximum number of skills to process per run |
--recent-window HOURS | Only consider sessions from the last N hours |
--sync-force | Force re-sync of already processed sessions |
--max-auto-grade N | Maximum auto-grade operations per run |
--loop | Run continuously |
--loop-interval SECS | Seconds between loop iterations (default: 3600) |
--help | Show command help |
Candidate actions
Each skill is assigned one of four actions during a run:| Action | Meaning |
|---|---|
evolve | Full evolution via replay and LLM rewrite |
package-search | Bounded mutation search across pre-generated variants (see below) |
watch | Re-evaluate recently deployed skills with no new evolution |
skip | Excluded — hit the --max-skills cap or missing required state |
Package search
When a skill has sufficient package-level evidence — specifically, an accepted frontier candidate from a prior search run — orchestrate routes it through package search instead of full evolution. Package search generates a bounded set of routing and body mutations for the skill, evaluates each variant, and applies the best-performing one. It is faster and more targeted than full evolution because it only explores changes within the skill’s existing structure. Run output includes two counters for this phase:package_searched— number of skills that entered the package search phasepackage_improved— number of skills where a winning variant was found and applied
--dry-run mode, package search is skipped and both counters report 0.
Continuous mode
selftune run is the lifecycle-first entrypoint for this runtime. Use
selftune orchestrate when you need the legacy command name explicitly or are
following low-level automation references. Use --review-required when you
want a stricter one-off run, or --dry-run to preview the plan without
mutating skill files.
For fully autonomous operation:
Concurrency
Orchestrate uses a lock file (~/.claude/.orchestrate.lock) to prevent concurrent runs. The lock is considered stale after 30 minutes.
Workflow skill proposals
After evolution and watch, orchestrate discovers multi-skill workflow patterns from telemetry and proposes new skills to formalize them. Proposals appear in the output as “Phase 6: Workflow Skill Proposals” and are persisted alongside the source skill. In--dry-run mode, proposals are discovered but not written to disk.
Priority system
Skills are processed in priority order:- Skills with improvement signals get +150 priority boost (capped at +450)
- Skills with lower pass rates get higher priority
- Skills that haven’t been evolved recently get a small boost