Update implementation plan files based on discussion
Scanned 9/2/2026
Install to Claude Code
npx -y skills add MarcusJellinghaus/mcp-workspace --skill plan_update --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Plan Update?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/marcusjellinghaus-plan-update)More formats (shields.io, HTML) on the badges page.
---
description: Update implementation plan files based on discussion
allowed-tools:
- mcp__mcp-workspace__read_file
- mcp__mcp-workspace__save_file
- mcp__mcp-workspace__edit_file
- mcp__mcp-workspace__list_directory
---
# Update Plan Files
Update the implementation plan files in `pr_info/steps` based on our discussion.
## Instructions
Update the plan by modifying the different files in folder `pr_info/steps`
Please do targeted changes.
Please log the decisions from our discussion in `pr_info/steps/Decisions.md`.
Only put those decisions that we discussed, no invented decisions.
(For each decision that you log, consider whether you discussed it with me and when I said so)
**Guidelines:**
- Make minimal, focused changes
- Preserve existing structure where possible
- Ensure consistency across all step files
- Update the summary if scope changes
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
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', ...