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

ASecurity

Run explicit org-based teamwork in LibrAgent. Use when collaboration needs durable org identity, org-visible child sessions, org-root resume behavior, or clear parent/sibling org context while preserving normal parent workspace inheritance.

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

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Org?

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

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

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

Files
SKILL.md
---
name: org
description: Run explicit org-based teamwork in LibrAgent. Use when collaboration needs durable org identity, org-visible child sessions, org-root resume behavior, or clear parent/sibling org context while preserving normal parent workspace inheritance.
---

# Org

Org is explicit lineage teamwork. It is not generic delegation and it is not scheduled automation.

Use `teamwork` first when the workspace constitution is not ready.
Use `org-restructure` when the org already exists and roles or constitution files need to change (add, layoff, merge, agents.md updates).

## Workflow

1. Confirm org is the right substrate.
   - Use org when the user wants org visibility, durable org identity, coordinator/specialist lineage, or root-session resume behavior.
   - If the real need is app-wide recurring or cron-like automation, stop and use `schedule`.
   - If the user only wants a clock delay or reminder inside the current conversation, stop and use `loop`.
   - If they want to resume when a process or ticket completes, stop and use `call-me-back`.
   - If the governing root session has not prepared the teamwork artifact directory yet, stop and use `teamwork` to call `agent__prepareTeamworkWorkspace()` first.
2. Read `.libragent/teamwork.json` before acting.
   - Confirm `executionSubstrate.mode` is `"org"` and `orgLineage.intended` is `true`.
   - If the manifest says a different substrate, reconcile before proceeding.
3. Keep one shared workspace.
   - Treat the app-local teamwork artifact directory as the SSOT for orchestration files.
   - The governing root session and org-visible children should keep the normal parent/override workspace inheritance model.
4. Create the org once from the root session.
   - Use `agent__createOrg(name="...")` from the governing root session.
   - Record the returned `orgId` and `orgName` in `coordination/DECISIONS.md` (the backend automatically updates `.libragent/teamwork.json` with these details).
   - The session that calls `agent__createOrg` becomes the org root. Do not call `agent__createOrg` again.
5. Spawn org-visible members explicitly.
   - Before creating a member for new work, inspect `agent__listAgents(type="sessions")` for an Idle org child with the same assistant ID and compatible workspace, then use `agent__messageToSession` (with `reset=true` for a fresh assignment) when reuse is safe.
   - Use `agent__spawnSession(configId, task)` for org-visible children only when no suitable member exists, a different role/workspace is needed, or additional parallel capacity is required. If the current session already belongs to the org, inheritance is automatic.
   - To keep a child out of Org view, spawn it from a session that is not part of an explicit org.
6. Resume through the org root.
   - The org root session is the canonical entry point. Org view should resume the root, not whichever child was last active.
   - If you need to identify the root, read `orgLineage.rootSessionId` from `.libragent/teamwork.json`.
7. Keep work anchored in the workspace constitution.
   - Read `agents.md`, `MISSION.md`, `ROLES.md`, and the coordination files before directing members.
   - Org context refines execution; it does not replace the shared workspace contract.

## Guardrails

- Do not invent a separate org-only workspace. Org members should inherit the parent effective workspace unless a task explicitly needs a different `workspaceOverride`.
- Do not use org identity for scheduled task groups or recurring automation.
- Do not treat arbitrary child-session resume as org resume. The org root is the entry point.
- Do not infer org membership from parent/child lineage alone — membership requires explicit org inheritance at session creation. Under an explicit org root that inheritance is automatic.
- After `agent__createOrg`, verify `.libragent/teamwork.json` contains the updated `orgId` and `rootSessionId` (written automatically by the backend).

## References

- [Org patterns and tool call examples](references/org-patterns.md)
- Living org changes (roles, constitution): use bundled skill `org-restructure`

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 →