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

Org Restructure

ASecurity

Restructure a living explicit org in LibrAgent without dissolving it. Use when an org already exists and you need to add/remove/merge roles in ROLES.md, update the org constitution (agents.md, MISSION.md), remove or retire org child sessions, reassign KANBAN owners, or record structural changes in coordination files. Not for initial org creation (use org), initial scaffolding (use teamwork), org dissolution, or archive.

10 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsshellrailsapibackend

Works with

api

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add fritzprix/libr-agent --skill org-restructure --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Org Restructure?

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

Security grade badge for Org Restructure
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fritzprix-org-restructure/badge)](https://www.skillsdirectory.com/skills/fritzprix-org-restructure)

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

Files
SKILL.md
---
name: org-restructure
description: Restructure a living explicit org in LibrAgent without dissolving it. Use when an org already exists and you need to add/remove/merge roles in ROLES.md, update the org constitution (agents.md, MISSION.md), remove or retire org child sessions, reassign KANBAN owners, or record structural changes in coordination files. Not for initial org creation (use org), initial scaffolding (use teamwork), org dissolution, or archive.
---

# Org Restructure

Tune an existing explicit org. This is evolution, not creation and not teardown.

Use `org` when the org does not exist yet or you need runtime coordination (spawn, resume, getOrg).
Use `teamwork` when the teamwork artifact directory or constitution files do not exist yet.

## Path conventions

Teamwork files live in the app-local artifact directory (Teamwork SSOT). Access them via:

- `@teamwork/...` aliases in agent tools
- `./.libragent/teamwork/...` from shell in the org root workspace

Do not edit repo-root copies unless the user explicitly wants repo pollution.

## Workflow

1. **Confirm this is restructure, not bootstrap.**
   - `.libragent/teamwork.json` must exist with `executionSubstrate.mode: "org"` and `orgLineage.intended: true`.
   - An `orgId` must already be set (from `agent__createOrg` or manifest).
   - If not, stop and use `teamwork` then `org`.
2. **Run pre-flight audit** — see [impact-analysis.md](references/impact-analysis.md).
3. **Pick one primary operation** (add, layoff, merge, constitution update, child removal). Load the matching reference checklist.
4. **Apply constitution + coordination changes** in dependency order (decision record → ROLES/MISSION/agents → KANBAN/HANDOFF → sessions).
5. **Propagate refresh** — constitution edits apply on a later execution step, not the current turn.
6. **Verify** with `agent__getOrg` and a quick coordination-file scan.

## Operation routing

| User intent | Read first | Primary edits |
| --- | --- | --- |
| Add a role | [constitution-update.md](references/constitution-update.md) | ROLES.md, MISSION.md, optional `skills/tf-*`, spawn child |
| Remove a role (layoff) | [layoff-checklist.md](references/layoff-checklist.md) | ROLES.md, KANBAN owners, HANDOFF, child sessions |
| Merge duplicate roles | [merge-checklist.md](references/merge-checklist.md) | ROLES.md, MISSION.md, skills, session mapping |
| Change operating rules | [constitution-update.md](references/constitution-update.md) | agents.md, DECISIONS.md |
| Remove child from org view | [layoff-checklist.md](references/layoff-checklist.md) § Child sessions | stop/delete session; no detach API yet |

## Core rules

1. **ROLES.md is the role contract; MISSION.md must stay in sync** when roles change. Update both in the same change set.
2. **Record every structural change** in `@teamwork/coordination/DECISIONS.md` before or alongside file edits.
3. **Reassign before you delete.** Move KANBAN owners and HANDOFF targets off a removed role before layoff or merge.
4. **Prefer org root for coordination.** Resume or message the root (`orgLineage.rootSessionId`) to broadcast constitution refresh.
5. **Do not call `agent__createOrg` again.** Restructure edits files and sessions; it does not recreate org identity.
6. **Refresh semantics:** after `agents.md` / `ROLES.md` edits, tell active members the new rules apply on their next execution step.

## Child session removal (current platform limits)

There is no `agent__detachFromOrg` tool today. To remove a session from org view:

- **Retire work:** `agent__stopSession(sessionId)` then `agent__deleteSession(sessionId)` if permanent removal is OK.
- **Keep work, hide from org:** not supported — document the limitation and ask the user to choose stop/delete or leave the session idle.

Passing `None` to `update_org_identity` exists in the backend but is not exposed as an agent tool.

## Guardrails

- Do not dissolve the org, delete the org root, or archive the entire teamwork artifact directory — out of scope.
- Do not remove the org root session from the org; the root is the canonical entry point.
- Do not edit only ROLES.md while leaving stale role sections in MISSION.md.
- Do not lay off a role while its tasks remain assigned to that role in KANBAN.md.
- Do not merge roles without picking one canonical agent ID and one primary artifact owner per merged responsibility.

## References

- [Impact analysis (pre-flight)](references/impact-analysis.md)
- [Layoff checklist](references/layoff-checklist.md)
- [Merge checklist](references/merge-checklist.md)
- [Constitution update](references/constitution-update.md)

Attribution

fritzprixfritzprix
View sourceMore from fritzprix →
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', ...

695601 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 →