Files
reliquary/docs/workpad/goals/lean-athanor-0.2.1.md
T

2.8 KiB

Goal: Lean Athanor optimization — Spire (version TBD; formerly 0.2.1)

Renumbered 2026-10-15: 0.2.2 shipped first (drop-superpowers-0.2.2); this goal gets its version when it is released. Set: 2026-10-05, Igor session 2026-10-05-21-athanor Builds on: lean-athanor (shipped as Spire 0.2.0). Feedback from dirigent and spacecraft implementation passes on 0.2.0 — and Codex's report on how it performs — feeds into this.

Success criteria

Learn from the first 0.2.0 runs

  • Run logs, journals and reviews from the first dirigent/spacecraft (and Codex) implementation passes on 0.2.0 are read, and what they show is reflected — fixes where the skill misled, nothing encoded from single incidents.

Trunk and forks is tested, not assumed

  • Preflight on a throwaway branch: is fork available; does a foreground fork block and return its result; what context and model does it start with; can it fork again; where does a background fork's completion go. Results land in implementation/references/spawning-claude-code.md with dates.
  • A trial on a real multi-phase plan (venue: dirigent or spacecraft, chosen with the user) compares trunk notes vs. forks for complex blocks. The skill keeps forks as an option or promotes them based on the result.

Project settings have a home

  • The spire:project template has a place for build settings the implementation skill reads: gate and test commands, worktrees on/off, explicit-path staging, owner-model defaults per block kind, standing brief constraints, whether the user sees the build plan before the run. (Landed in 0.2.2, 2026-10-15: ## Build section plus a gitignored project.local.md override.)

Models and roles

  • Decided whether pinned 5.5 planner/reviewer role agents are worth adding, or whether the stamped-id check in Igor is enough. (2026-10-15, user: both — planner, attacker, reviewer pinned to Opus 5.5, and Igor keeps checking stamped ids. Landed in 0.2.2.)
  • Pinky (brainstorm partner) exists as an agent pinned to Opus 4.6 — the "understanding the human" interpreter — or the decision not to build it is recorded. All other Opus-pinned Spire agents stay on 5.5.

Small fixes

  • The "Planned implementation" delegation row (Igor skill and model-tiers.md) says the plan must have been attacked first. (Landed in 0.2.2, 2026-10-15 — see drop-superpowers-0.2.2.)

Later (not 0.2.1)

  • Mining journals for deeper insights.
  • Orchestrator introspection of subagent token use / signals into running work (dirigent is exploring this). Until then, context sizes stay guesstimates.
  • Swappable plan-writing approaches (grill-me, our own playbook).