docs(roadmap): #347 goal-mode research (no native CC primitive) - #348
Merged
Conversation
Records research findings on whether Claude Code has a primitive equivalent to Codex's $gdlc goal mode for long-running goal-bound work. Verdict: NO native primitive. Closest path is GOAL.md template + SessionStart hook + UserPromptSubmit reassertion + extension to the existing /sdlc skill (not a new skill trio, per Prove-It Gate absorption principle). Implementation deferred. Research artifact at .reviews/347-goal-mode-research.md (gitignored, summarized in entry) documents the 7 CC primitives checked and why each falls short, plus the 5-step build sequence for when this is picked up. Trigger to revisit: second user request, or maintainer hits the gap in their own work.
This was referenced May 24, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Records research findings for issue #347 (Claude equivalent for Codex goal-mode workflow) and defers implementation.
What changed
Verdict
NO native CC primitive for goal mode. Sessions are independent JSONL files; persistence is indirect via `CLAUDE.md`, auto memory, and hooks. The closest path is exactly the wizard's existing pattern (skill + SessionStart hook + project file), just unwrapped for goal-mode semantics.
Per-feature mapping (verified against CC docs 2026-05-23)
Prove-It Gate decision
Absorb into existing `/sdlc` skill as a "Long-Running Goal Mode" section + `GOAL.md`/`HANDOFF.md` templates rather than building a new `/goal-start`/`/goal-handoff`/`/goal-stop` skill trio. Per #236 functional bloat principle: default to absorption; promote to dedicated skill only if absorbed form proves too easy to ignore.
Why deferred
Only one demand signal (issue author). Per #233 pattern, build when a second user requests OR when the maintainer's own work hits the goal-mode gap. The roadmap entry has the full 5-step implementation sequence for cold pickup.
Research artifact
`.reviews/347-goal-mode-research.md` (gitignored per `.reviews/` convention from #236, content summarized in roadmap entry).
Test plan