docs(maxsim-batch): add tier selection table and graceful degradation (§7.2)#188
docs(maxsim-batch): add tier selection table and graceful degradation (§7.2)#188maystudios merged 1 commit intomainfrom
Conversation
… to SKILL.md Adds the §7.2-required Tier Selection Logic decision table showing which workflows use Tier 1 subagents vs Tier 2 Agent Teams, and a Graceful Degradation section with the exact fallback message when Agent Teams are unavailable. Brings the §7.2 Parallelism Strategy audit to 100%. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
Updates the maxsim-batch skill documentation to fully capture the Tier 1 vs Tier 2 decision guidance and the expected fallback behavior when Agent Teams are unavailable, aligning the skill with the Parallelism Strategy spec in PROJECT.md §7.2.
Changes:
- Adds a “Tier Selection Logic” decision table mapping workflow types to Tier 1 (Subagents) vs Tier 2 (Agent Teams).
- Adds a “Graceful Degradation” section describing Tier 1 fallback and the exact user-facing message to display.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| ### Tier Selection Logic | ||
|
|
||
| MaxsimCLI chooses the tier automatically based on the workflow: | ||
|
|
There was a problem hiding this comment.
The new Tier Selection Logic section states that “MaxsimCLI chooses the tier automatically based on the workflow”, but this conflicts with the preceding “Current status” note that Tier 2 workflow templates are not yet implemented and all workflows currently run Tier 1. Consider clarifying that this table describes the intended/spec selection logic once Tier 2 templates exist (or otherwise reconcile these statements).
| If Agent Teams are unavailable (env var `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` not set, unsupported plan, or feature not yet stable), MaxsimCLI falls back to Tier 1 subagents for all workflows. Inform the user with this exact message: | ||
|
|
||
| > "Competitive mode: using Tier 1 subagents (Agent Teams not available or not required for this strategy). Each executor works independently; verifier selects the best result." | ||
|
|
There was a problem hiding this comment.
The Graceful Degradation section says Tier 1 fallback applies “for all workflows” and instructs using an “exact message”, but the message itself is specific to “Competitive mode”. If this message is only meant for competitive implementation fallback (as in the execute workflow template), consider scoping this section/message to competitive mode, and/or documenting the user-facing message(s) for other workflow degradations separately to avoid misleading guidance.
| If Agent Teams are unavailable (env var `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` not set, unsupported plan, or feature not yet stable), MaxsimCLI falls back to Tier 1 subagents for all workflows. Inform the user with this exact message: | |
| > "Competitive mode: using Tier 1 subagents (Agent Teams not available or not required for this strategy). Each executor works independently; verifier selects the best result." | |
| If Agent Teams are unavailable (env var `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` not set, unsupported plan, or feature not yet stable), MaxsimCLI falls back to Tier 1 subagents for all workflows. | |
| For **competitive implementation / competitive mode** workflows, inform the user with this exact message: | |
| > "Competitive mode: using Tier 1 subagents (Agent Teams not available or not required for this strategy). Each executor works independently; verifier selects the best result." | |
| For other workflows, clearly inform the user that Agent Teams are unavailable and that Tier 1 subagents are being used instead, using wording appropriate to that workflow. |
|
🎉 This PR is included in version 5.14.0 🎉 The release is available on: Your semantic-release bot 📦🚀 |
Summary
templates/skills/maxsim-batch/SKILL.md, mapping each workflow type to Tier 1 (Subagents) or Tier 2 (Agent Teams) with a rationale columnCLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMSis unavailableTest plan
npx vitest run— 548 tests pass (18 suites)npm run build— TypeScript compiles and assets copy cleanlynpm run lint— Biome exits 0 (pre-existing warnings only, none in changed file)🤖 Generated with Claude Code