Skip to content
Back to skills

Plan Doc

ASecurity

Create a living Axl plan or design doc grounded in developer journeys, requirements, acceptance criteria, architecture, implementation phases, and safe parallelization. Use only when the user explicitly invokes $plan-doc for a named body of work.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 18, 2026
ai-agents

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 18, 2026

npx -y skills add axl-sdk/axl --skill plan-doc --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Plan Doc?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Plan Doc
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/axl-sdk-plan-doc-axl/badge)](https://www.skillsdirectory.com/skills/axl-sdk-plan-doc-axl)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: plan-doc
description: Create a living Axl plan or design doc grounded in developer journeys, requirements, acceptance criteria, architecture, implementation phases, and safe parallelization. Use only when the user explicitly invokes $plan-doc for a named body of work.
---

# Plan Doc

Create the living plan requested by the user by following
`.claude/skills/plan-doc/references/procedure.md` (also linked as
`references/procedure.md` beside this file; read it now). This file binds the
procedure's lanes to Codex.

## Lane bindings

| Lane                  | Agent                                                                                |
| --------------------- | ------------------------------------------------------------------------------------ |
| Discovery             | `Explore`                                                                            |
| Review, plan charter  | `reviewer` for established architecture; `senior-reviewer` for consequential changes |
| Blind analyst, opt-in | `senior-reviewer` with the blind-analyst charter                                     |

## Platform mechanics

- Start reviewers and blind analysts in fresh context (`fork_turns="none"` when the host exposes that option). Supply raw requirements and artifacts, not the implementation conversation or persuasive rationale. A blind analyst receives only requirements and public behavior until its matrices are frozen.
- Plan mode: present the full document through the available plan-approval workflow; write to `.internal/plans/` only after approval.

Files in this skill

  • SKILL.md1.5 KB
  • agents/openai.yaml223 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.