Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

00.Feat 260525014.Done.Planner Subagent

ASecurity

`/agn:design epic` and `/agn:design feature` are placeholders pending the Planner. They should perform focused design revisions on existing units by delegating to the Planner in refine mode.

2 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agents

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add vkroz/taskman --skill 00.feat-260525014.done.planner_subagent --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of 00.Feat 260525014.Done.Planner Subagent?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for 00.Feat 260525014.Done.Planner Subagent
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vkroz-00-feat-260525014-done-planner-subagent/badge)](https://www.skillsdirectory.com/skills/vkroz-00-feat-260525014-done-planner-subagent)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
00.task-260526000.done.create_design_skill.md
---
id: '260526000'
type: task
status: done
priority: '00'
slug: create_design_skill
title: Wire design skill to Planner
---

# Wire design skill to Planner

# Wire design skill to Planner

## Problem statement

`/agn:design epic` and `/agn:design feature` are placeholders pending the Planner. They should perform focused design revisions on existing units by delegating to the Planner in refine mode.

## Scope

In scope:
- Edit `plugins/agn/skills/design/SKILL.md`.
- Replace epic and feature placeholders with delegation steps that call the Planner with `mode=refine, level=<level>, path=<existing unit>`.
- Keep the product branch as-is (architecture.md drafting still happens in the parent).
- Define the user-facing flow: locate existing unit → call Planner refine → present diff → write back via taskman.sh (status preservation, no folder move).

Out of scope:
- The product branch's architecture.md flow.
- The Planner system prompt (covered by `create_planner_subagent`).
- Define and plan skills (sibling tasks).

## Acceptance criteria

- Epic branch delegates to Planner in refine mode.
- Feature branch delegates to Planner in refine mode.
- Refinement does not create a new unit — it operates on the existing file's body.
- Product branch unchanged.

## Quality gates

- Skill body parses as markdown; YAML frontmatter intact.
- Each branch has explicit dispatch logic.

## Summary

### Steps completed

1. Updated YAML `description` to drop "once the planner_subagent feature ships" — Planner ships in this same feature.
2. Replaced epic placeholder with a 6-step refinement workflow: Locate → Identify gap → Delegate to Planner (refine mode) → User review → In-place persist via Edit → Report. Added Discipline notes (no folder moves, redirect re-decomposition to `/agn:plan epic`).
3. Replaced feature placeholder with the parallel feature-level workflow (locate, identify, delegate, review, persist, report; includes linked spec in the upstream list and as a possible edit target).
4. Product branch left untouched (architecture.md drafting works in parent session as before).

### Changes made

Modified:
- `plugins/agn/skills/design/SKILL.md` (3 surgical edits: YAML description + 2 placeholders)

### Notable decisions

- **Refinement is in-place.** The design skill edits the existing file's body sections directly; no new unit, no folder move, no slug change. This matches the user expectation that `/agn:design` doesn't restart the lifecycle.
- **Design ≠ Plan, made explicit in Discipline.** Each branch redirects "I want to add/remove features" to `/agn:plan`. Keeps the two skills from drifting into the same job.

### Links

- Modified file: `plugins/agn/skills/design/SKILL.md`
- Sibling task: `create_planner_subagent` (defines the Planner)

Attribution

vkrozvkroz
View sourceMore from vkroz →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →