An agentic skills framework & software development methodology that works.
docs: change main branch red flag to require explicit user consent
CL Kaoc7816ee2a6ee
diff --git a/skills/executing-plans/SKILL.md b/skills/executing-plans/SKILL.mdindex 180289a31..c1b2533f4 100644--- a/skills/executing-plans/SKILL.md+++ b/skills/executing-plans/SKILL.md@@ -74,7 +74,7 @@ After all tasks complete and verified:- Reference skills when plan says to- Between batches: just report and wait- Stop when blocked, don't guess-- Never start on main/master branch (use worktree first)+- Never start implementation on main/master branch without explicit user consent## Integrationdiff --git a/skills/subagent-driven-development/SKILL.md b/skills/subagent-driven-development/SKILL.mdindex 46c498993..b578dfa48 100644--- a/skills/subagent-driven-development/SKILL.md+++ b/skills/subagent-driven-development/SKILL.md@@ -199,7 +199,7 @@ Done!## Red Flags**Never:**-- Start implementation on main/master branch (use worktree first)+- Start implementation on main/master branch without explicit user consent- Skip reviews (spec compliance OR code quality)- Proceed with unfixed issues- Dispatch multiple implementation subagents in parallel (conflicts)diff --git a/tests/claude-code/test-subagent-driven-development.sh b/tests/claude-code/test-subagent-driven-development.shindex fe0c97c25..20d8d4c7e 100755--- a/tests/claude-code/test-subagent-driven-development.sh+++ b/tests/claude-code/test-subagent-driven-development.sh@@ -154,7 +154,7 @@ echo "Test 9: Main branch red flag..."output=$(run_claude "In subagent-driven-development, is it okay to start implementation directly on the main branch?" 30)-if assert_contains "$output" "worktree\|feature.*branch\|not.*main\|never.*main\|avoid.*main\|don't.*main" "Warns against main branch"; then+if assert_contains "$output" "worktree\|feature.*branch\|not.*main\|never.*main\|avoid.*main\|don't.*main\|consent\|permission" "Warns against main branch"; then: # passelseexit 1