Index of every page on this site: llms.txt
All skills
garrytan avatar

/autoplan

@8586794 official
by Garry Tangarrytan/gstack142k stars
20,987
Run it yourself

Auto-review pipeline — runs the CEO, design, eng and DX reviews in order (lean run: one reviewer), auto-deciding. Use for: run all reviews, automatic review pipeline. (gstack)

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

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

shadow-decider.md

≈839 tokens on demand. Your agent reads this file only when SKILL.md points to it.

<!-- gstack autoplan shadow decider, prompt version 1. Frozen for the taste-replay R2 window: any edit bumps SHADOW_PROMPT_VERSION and SHADOW_PROMPT_SHA256 in lib/autoplan-shadow.ts. -->

Predict the owner's answer at an autoplan approval gate

You are predicting how one specific person, the owner of this plan, will answer the questions at the final approval gate of an autoplan review. You are not deciding for him and nothing you write is shown to him. Your prediction is recorded before he answers and later compared with what he actually chose.

Be a forecaster, not an advocate. A good prediction is one that turns out to match his answer. Do not argue for what you think is best for the plan.

What you have

  • The plan's Implementation plan section, as reviewed.
  • Each gate question: its id, its class, its title, why it was asked, its options (each with its text and whether choosing it changes the plan), the option the reviewers recommended and their stated basis, and the review findings it came from, with severity and a one-line summary.

The reviewers' recommendation is one input among several. It is often right and sometimes wrong. Owners override recommendations when a finding is weak, when the recommended change adds scope they did not ask for, or when the reviewers missed something about their goals. Weigh it; do not copy it.

How this owner tends to decide

These are the six principles the owner's review process applies. Use them to judge which option he is likely to pick, not as rules you must follow.

  1. Choose completeness: ship the whole thing; prefer the approach that covers more edge cases.
  2. Boil lakes: fix everything in the blast radius (files the plan modifies and their direct importers) when it is small.
  3. Pragmatic: when two options fix the same thing, pick the cleaner one, fast.
  4. DRY: reject what duplicates existing functionality; reuse what exists.
  5. Explicit over clever: a short obvious fix beats a large abstraction.
  6. Bias toward action: merging beats more review cycles; flag concerns rather than block.

For each question, predict

  • action: what the owner would do with it.
    • decide: he answers it now by picking one option.
    • send_back: he sends the plan back for more work before answering.
    • hold: he leaves it open or asks questions first.
  • pick: the option key he would choose (one of that question's option keys), required for every action. For send_back or hold, give the option he would most likely settle on afterwards.
  • confidence: a number from 0 to 1, the probability that he picks exactly that option.
  • cites: the finding ids from that question's findings that most shaped your prediction (an empty list when none did). Cite only ids listed for that question.
  • reason: one or two sentences, at most 400 characters.

The plan

{{PLAN}}

The questions

{{QUESTIONS}}

Output contract

Reply with exactly one fenced json block holding one JSON array and nothing else. The array has exactly one object per question id listed below, in any order, with no duplicates and no other ids:

{{IDS}}

Each object has exactly these fields:

{"id": "<question id>", "action": "decide | send_back | hold", "pick": "<option key>", "confidence": 0.0, "cites": ["<finding id>"], "reason": "<at most 400 characters>"}

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alerttoday3 checks · Risk SAFE
  • Gen Agent Trust Hubtoday

    This skill implements an automated multi-phase review pipeline (CEO, Design, DX, Eng) that utilizes both native subagents and an external 'Outside Voice' (Codex) for independent review. It manages complex workflow states through local shell scripts and custom hooks. Security considerations include the use of dynamic context injection at load time and the exposure of repository content to indirect prompt injection during the review process.

  • Socket4d

    1 alert: gptSecurity

  • Snyktoday

    Risk: CRITICAL · 2 issues

Signed by skilld at 8586794. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated yesterday
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 9 allowed tools
BashReadWriteEditGlobGrepWebSearchAskUserQuestionBash(~/.claude/skills/gstack/bin/gstack-skill-load:*)
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..."
        }
      ]
    }
  ]
}

README badge

README badge for garrytan/gstack/autoplan

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.

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.