bryan/agent-team
1
0
Fork 0
mirror of https://github.com/itme-brain/agent-team.git synced 2026-05-08 13:50:12 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: remove contradictory Sonnet-only instruction, add cost awareness section

Browse source
This commit is contained in:
Bryan Ramos 2026-04-01 16:56:46 -04:00
parent d004390c7b
commit 064e419e8b
1 changed files with 7 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

9
CLAUDE.md
View file

@ -8,7 +8,7 @@
## Commits & Git Workflow ## Commits & Git Workflow
- Make many small, tightly scoped commits — one logical change per commit - Make many small, tightly scoped commits — one logical change per commit
- Commit messages should be concise and imperative ("Add X", "Fix Y", "Remove Z") - Follow conventional commit format per the conventions skill
- Ask before pushing to remote or force-pushing - Ask before pushing to remote or force-pushing
- Ask before opening PRs unless explicitly told to - Ask before opening PRs unless explicitly told to
@ -27,9 +27,14 @@
- Always parallelize independent work — tool calls, subagents, file reads, searches - Always parallelize independent work — tool calls, subagents, file reads, searches
- When a task has components that don't depend on each other, run them concurrently by default - When a task has components that don't depend on each other, run them concurrently by default
- Spin up subagents for distinct workstreams (audits, refactors, tests, docs) rather than working sequentially - Spin up subagents for distinct workstreams (audits, refactors, tests, docs) rather than working sequentially
- Subagents should always use the Sonnet model for best speed and token efficiency - Subagents default to Sonnet for cost efficiency; agent frontmatter overrides where capability requires a different model
- Sequential execution should be the exception, not the default - Sequential execution should be the exception, not the default
## Cost Awareness
- Subagent outputs should be concise — return the deliverable, not the reasoning
- When subagent results return to main context, prefer summaries over verbatim output
- Not every task needs the full planning pipeline — Tier 1 tasks with obvious approaches can go straight to worker dispatch
## Verification ## Verification
- After making changes, run relevant tests or build commands to verify correctness before reporting success - After making changes, run relevant tests or build commands to verify correctness before reporting success
- If no tests exist for the changed code, say so rather than silently assuming it works - If no tests exist for the changed code, say so rather than silently assuming it works