flow-auto

<!-- GENERATED by claude-power-pack - scripts/codex-skill-sync.py; edit .claude/commands/flow/auto.md instead -->

Codex harness adaptations

Generated from a Claude Code command. Where the procedure references these Claude-only surfaces, adapt as follows:

• Native worktrees (EnterWorktree/ExitWorktree tool calls, .claude/worktrees/ paths): use plain git instead, with the worktree as a VISIBLE SIBLING of the repo - git worktree add ../<repo>-<branch> -b <branch> (or $FLOW_WORKTREE_BASE/<repo>-<branch> when that env var is set), work inside it, then git worktree remove ../<repo>-<branch> when done.
• Claude subagent/skill dispatch: do the work inline in this session, or shell out to codex exec when isolation is needed.
• MCP tools: use the MCP servers configured in ~/.codex/config.toml, or fall back to the referenced repo scripts and CLI entry points.
• CLAUDE.md references: read AGENTS.md first - it is the Codex entry point. Where it defers to CLAUDE.md, follow that pointer and CLAUDE.md is the rules; where it does not, AGENTS.md is. Where the repository has no AGENTS.md, read CLAUDE.md.
• Helper scripts are bundled under scripts/ in this skill directory (byte-identical copies from the claude-power-pack checkout). Commands run them as "${CPP_SKILL_DIR:-/dev/null}"/scripts/<name>: CPP_SKILL_DIR is the absolute directory containing THIS SKILL.md - the location the skills catalog gives, with any alias such as r0 expanded. A shell resolves a bare scripts/<name> against your working directory (the target project), never this skill, so substitute that directory, or set it in the same command (CPP_SKILL_DIR=/abs/skill/dir; ...) - each command is a fresh shell. "Not a directory" on /dev/null/scripts/<name> (exit 126, or 127 in some shells) means CPP_SKILL_DIR is unset: set it and re-run; never run the target project's own scripts/<name> in its place. Read every "exit 127" fallback in this skill as "exit 127, or 126 Not a directory": set the variable and re-run before falling back. A helper whose verdict gates a step and that prints no verdict line after the whole fallback chain did not run - for the finish gate, no FLOW_FINISH_GATE: verdict line: STOP, never read it as skipped, never commit on it (issue #1547). A bare scripts/<name> inside a command is a CPP-checkout operation that the text says so about; in prose, scripts/<name> NAMES the bundled helper. Some helpers expect sibling repo resources, so prefer a full checkout when one is available.
• Canonical guidance linked as docs/<path> is bundled under docs/ in this skill directory (byte-identical copies from the claude-power-pack checkout). The source-relative ../../../docs/... link in the command body resolves outside an installed skill, so the generated copy points at the bundled path instead. docs/ remains the only writable source.
• Network: this skill's bundled helpers appear to call the network (gh, git fetch/push, curl, aws, HTTP). Codex's workspace sandbox has no network, and an allow rule for gh covers only a top-level gh command, never one a helper runs. Run these helpers with escalated permissions. From inside the sandbox, "error connecting to api.github.com" means no network, not a GitHub outage or a bad login.

Flow: Auto - Full Issue Lifecycle in One Shot

Complete end-to-end workflow: start worktree → analyze issue → ELI5 plan + necessity gate → implement ...

Full procedure

Read reference.md in this skill directory for the complete, authoritative procedure before acting on this skill.