skilld
All skills
garrytan avatar

/autoplan

@dcaea52 official
by Garry Tangarrytan/gstack135k stars
20,051

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)

Requires /gstack-upgrade /plan-tune /retro /ship /qa-only /document-generate /context-save /learn /qa /review /office-hours

Ask your Agent

Use this Skill: https://skilld.dev/gh/garrytan/gstack/autoplan

This session only. Nothing lands on disk.

sectionsphase-close.md

≈1.1k tokens on demand. Your agent reads this file only when SKILL.md points to it.

<!-- AUTO-GENERATED from phase-close.md.tmpl — do not edit directly --> <!-- Regenerate: bun run gen:skill-docs -->

Read this section afresh when the current phase's review work finishes. Use the phase, amendment checkpoint and methodology path bound at that phase's exit. This procedure owns readback, verification and publication as separate operations. On hosts that inline sections, reread this close block in the installed Autoplan SKILL.md at each exit; those hosts do not have a separate phase-close.md file.

  1. Finish and save the review. Require the phase's full methodology/section Reads, required outputs, successful writes and terminal reviewer results. Match a completed native review's INPUT to its voice snapshot. A pending reviewer keeps the phase open. Apply the phase's failure policy to failed native attempts; unavailable/disabled voices receive no completion credit.
  2. Reconcile accepted requirements. Record every accepted behavior, condition, test and manual checklist in this phase's accepted block. Taste remains provisional; User Challenges preserve the original requirements. A None record must explain why the implementation remains unchanged. Keep the amendment checkpoint fixed for this invocation, including after compaction.
  3. Prepare this phase's close packet. Run with the exit's phase/checkpoint:
bun "<SNAPSHOT_TOOL>" prepare-close "<PHASE>" "<ACTIVE_PLAN>" "<AMENDMENT_CHECKPOINT>" "<RESTORE_PATH>" "<methodologyPath>"

This applies accepted requirements and exports an immutable packet with the full current implementation, fixed checkpoint, hashes and phase-specific report fields. The blind reviewer input stays unchanged. These are inputs to steps 4–6 below; preparation does not perform them. 4. Read the complete current packet. For every returned readRanges entry, issue a Read of closePacketPath with that entry's exact offset and limit. Finish all ranges through EOF. A Read of only the edited tail does not satisfy this step; previous snapshots do not satisfy it. If a result is truncated, read its missing ranges. If a Read fails, repair it and finish the missing ranges. Do not advance on a request without its result. After the final successful Read, perform step 5 here. 5. Verify the current implementation. Compare the complete current implementation with accepted decisions, source requirements, conditions, tests and required outputs. Retention checks prove bytes; counts, hashes, keyword probes and a saved “Read-back” sentence do not perform this semantic review. Review history stays in Review record. Recheck step 1's prerequisites. If any prerequisite is incomplete, keep this phase open and finish the missing work. Fix omissions, then regenerate the packet with the same checkpoint and Read the entire new packet before publication. Any later implementation or accepted-decision edit returns to step 3, including after compaction. 6. Publish the parent report. After successful verification, SEND the filled report below now as visible parent assistant text, using actual findings and voice statuses. This message is the next operation before any next-phase tool call. Use the packet's report fields for this phase, the actual host's reviewer names, and N/A when either review voice is missing; confirmed counts require both voices. Include the DX metrics line only when report.includeDxMetrics is true. Resolve report.next using the driver's applicable scope/skip rules.

Phase <report.number> complete. [DX only: DX overall: <score>/10. TTHW: <observed> min → <target> min.] Outside review: <completed: N concerns / unavailable / disabled>. Native subagent: <completed: N issues / unavailable>. Consensus: <N/A (voice coverage missing) | X/<report.total> native+outside confirmed; Y disagreements → gate>. Passing to <applicable report.next>.

  1. Return to the driver. After sending the actual parent report, continue to the driver in the same turn. The driver alone advances phases and emits applicable skip messages; a skip is never a completion. Do not wait for a “continue” reply.

The sent conversation message is step 6's output. Saving it in ACTIVE_PLAN or printing it through Bash does not publish it. After compaction, reconcile the bound packet and actual sent messages: a verified phase without its announcement resumes at step 6; stale inputs return to step 3. A helper result or Read completes neither verification nor publication.

Source: SKILL.md on GitHub

Third-party checks

1 warning5d3 checks · Risk SAFE
  • Gen Agent Trust Hub5d

    The autoplan skill is a sophisticated review orchestrator that sequences strategic (CEO), user experience (Design/DX), and technical (Eng) reviews. It uses a robust internal 'publication hook' to ensure workflow integrity by verifying that all required methodology reads and review steps are completed before progressing. The skill integrates with external models via the Codex CLI and relies on local bash scripts for state management, incorporating multiple layers of validation and safety prompts to mitigate risks from processed data.

  • Socket5d

    5 alerts: gptAnomaly

  • Snyk5d

    Risk: LOW · No issues

Provenance

Signed by skilld at dcaea52. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 15 hours ago.

Activeupdated 2 days ago

Capability

What it can do
Runs commands Reads files Edits files Network
preamble-tier
3
version
1.0.0
triggers
[
  "run all reviews",
  "automatic review pipeline",
  "auto plan review"
]
All 8 allowed tools
BashReadWriteEditGlobGrepWebSearchAskUserQuestion
Other metadata
hooks
{
  "PreToolUse": [
    {
      "matcher": "Read",
      "hooks": [
        {
          "type": "command",
          "command": "bash -c 'S=\"$HOME/.claude/skills/gstack/autoplan/bin/phase-publication-hook\"\nif [ -f \"$S\" ]; then exec bash \"$S\"; fi\nprintf '\\''%s\\n'\\'' '\\''{\"hookSpecificOutput\":{\"hookEventName\":\"PreToolUse\",\"permissionDecision\":\"deny\",\"permissionDecisionReason\":\"Autoplan publication guard is unavailable. Restore the installed autoplan/bin/phase-publication-hook before continuing this skill.\"}}'\\'''",
          "statusMessage": "Checking Autoplan phase publication..."
        }
      ]
    },
    {
      "matcher": "Agent",
      "hooks": [
        {
          "type": "command",
          "command": "bash -c 'S=\"$HOME/.claude/skills/gstack/autoplan/bin/phase-publication-hook\"\nif [ -f \"$S\" ]; then exec bash \"$S\"; fi\nprintf '\\''%s\\n'\\'' '\\''{\"hookSpecificOutput\":{\"hookEventName\":\"PreToolUse\",\"permissionDecision\":\"deny\",\"permissionDecisionReason\":\"Autoplan publication guard is unavailable. Restore the installed autoplan/bin/phase-publication-hook before continuing this skill.\"}}'\\'''",
          "statusMessage": "Checking Autoplan phase publication..."
        }
      ]
    }
  ]
}

Topics

README badge

README badge for garrytan/gstack/autoplan

What it does

Runs CEO, design, eng, and DX review skills sequentially with automated decision-making using six decision principles, surfaces taste decisions at a final approval gate. Targets the gstack review workflow and eliminates 15-30 intermediate questions by auto-deciding on close calls and codex disagreements.

Generated from the current SKILL.md.

Frequently asked

What does autoplan do?
Autoplan reads the CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. It surfaces taste decisions at a final approval gate so you get a fully reviewed plan in one command.
When should I use autoplan instead of running reviews manually?
Use autoplan when you have a plan file and want to run the full review gauntlet without answering 15-30 intermediate questions. It's useful when asked to 'auto review', 'autoplan', or 'make the decisions for me'.
What tools does autoplan use?
Autoplan uses Bash, Read, Write, Edit, Glob, Grep, WebSearch, and AskUserQuestion to load and execute the review skills sequentially.
Does autoplan work in plan mode?
Yes. In plan mode, autoplan takes precedence over generic plan mode behavior. Follow the skill file step by step starting from Step 0, and the first AskUserQuestion satisfies plan mode's end-of-turn requirement.

Generated from the current SKILL.md. These answers refresh after source changes.