← ClaudeAtlas

developlisted

Minimal codex-native develop loop. Use for implementation tasks with linear plan-build-verify flow and measurable quality gates.
Borda/AI-Rig · ★ 19 · AI & Automation · score 71
Install: claude install-skill Borda/AI-Rig
# Develop Run a linear implementation loop with strict gates. ## Input Schema ```json { "goal": "required implementation objective", "constraints": [ "optional constraints" ], "done_when": "required acceptance statement" } ``` ## Workflow (Exact Commands) 1. Create run directory. ```bash TS=$(date -u +%Y-%m-%dT%H-%M-%SZ) OUT_DIR=".reports/codex/develop/$TS" mkdir -p "$OUT_DIR" ``` 2. Record baseline diff and branch. ```bash git rev-parse --abbrev-ref HEAD >"$OUT_DIR/branch.txt" git diff --stat >"$OUT_DIR/before.diffstat" ``` 3. Define the narrowest reversible change, ownership, and acceptance criteria. If the task is 3+ steps or has design tradeoffs, update the plan before editing. 4. Run the anti-rationalization gate before editing. - Existing code and tests for the target surface have been read. - Failure mode or new behavior is captured by a failing doctest, pytest, or explicit acceptance check. - If the task starts from a symptom, failing test, failing CI, flaky behavior, regression, tool/environment error, or unexplained metric shift, run `investigate` first or document equivalent root-cause evidence before editing. - Root-cause evidence includes the claim, supporting logs/code, a falsification check, and at least one rejected alternative. A workaround-only change is a temporary mitigation, not completion, unless explicitly requested by the user. - Behavior-preserving refactors have characterization tests o