Release version 5.5.0, adding a mandatory sizing gate to /team so orc… - #4
Merged
Conversation
…hestration cost tracks task size. A measured 5-file change cost 905 API calls and 131.6M billed-equivalent tokens across 7 sessions in 37 minutes. Three rules in commands/team.md caused it. The scope table read as a floor rather than a ceiling, so a 5-file diff drew 6 agents. Step 1 is now a sizing gate with four tiers (Direct 0 / Small 1 / Medium 2-3 / Large 3-5). The lead states its tier and agent count before dispatching, and ambiguity resolves downward. The Anti-Stop Rule told the lead to continue its own work after dispatch, which produced 75 lead-side Bash calls duplicating what six agents were already doing. "Continue" now scopes to orchestration only; editing, running the app, container exec and test runs are forbidden while agents are live. Polling with ListAgents is banned outright — it cost 12 calls at roughly 186K context each. security-auditor and test-engineer were unconditional. Both are now trigger-gated, with five conditions for security and three for tests. Adds a Cost rule section and bans the research-then-re-derive pattern that cost 7.5M tokens when two research agents were dispatched and the implementer re-derived their findings anyway. Bumps all 7 declared version files to 5.5.0 and documents the release in CHANGELOG.md. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
…hestration cost tracks task size.
A measured 5-file change cost 905 API calls and 131.6M billed-equivalent tokens across 7 sessions in 37 minutes. Three rules in commands/team.md caused it.
The scope table read as a floor rather than a ceiling, so a 5-file diff drew 6 agents. Step 1 is now a sizing gate with four tiers (Direct 0 / Small 1 / Medium 2-3 / Large 3-5). The lead states its tier and agent count before dispatching, and ambiguity resolves downward.
The Anti-Stop Rule told the lead to continue its own work after dispatch, which produced 75 lead-side Bash calls duplicating what six agents were already doing. "Continue" now scopes to orchestration only; editing, running the app, container exec and test runs are forbidden while agents are live. Polling with ListAgents is banned outright — it cost 12 calls at roughly 186K context each.
security-auditor and test-engineer were unconditional. Both are now trigger-gated, with five conditions for security and three for tests.
Adds a Cost rule section and bans the research-then-re-derive pattern that cost 7.5M tokens when two research agents were dispatched and the implementer re-derived their findings anyway.
Bumps all 7 declared version files to 5.5.0 and documents the release in CHANGELOG.md.