Skills for Real Engineers. Straight from my .agents directory.
agent-severance
Agent skill frommohitagw15856/pm-claude-skills
Offboard an AI agent the way you'd offboard an employee — inventory what it knew and touched, export then purge its memory, revoke every credential and access grant, and write the handover for its successor (human or agent). Use when decommissioning an agent or bot, switching agent vendors, ending an AI pilot, or when someone asks 'what did this thing have access to?'. Produces a severance checklist, an access-revocation table, a memory disposition record, and a successor handover.
How to install agent-severance
npx skills add mohitagw15856/pm-claude-skills# or add only this skill to Claude Code: copy the folder
skills/agent-severance/
# into
~/.claude/skills/agent-severance/ (all projects)
.claude/skills/agent-severance/ (one project)
1# Agent Severance Skill23Orgs learned employee offboarding the hard way: the contractor whose VPN worked4for a year after the contract, the shared password nobody rotated. Long-lived5agents recreate every one of those failure modes with worse logging — an agent6accumulates credentials, memory, integrations, scheduled jobs, and undocumented7responsibilities, and then one day it's "turned off" by deleting a chat window8while its API keys live on. This skill runs the severance properly: know what9it had, keep what's valuable, kill what's live, and hand over what it did.1011## What This Skill Produces1213- An **inventory**: everything the agent could touch (credentials, tools, data14 stores, channels), everything it knew (memory, context files, fine-tuning or15 instructions), and everything it *did on a schedule*16- An **access-revocation table** with owner and verification step per row —17 revoked isn't revoked until someone confirmed the key is dead18- A **memory disposition record**: exported / retained (where, why, how long) /19 purged (how verified) — the part compliance will ask about in 202720- A **successor handover**: the agent's actual duties, including the21 undocumented ones users discovered, for whoever inherits them2223## Required Inputs2425Ask for (if not already provided):26- The agent: platform, what it was for, how long it ran, who owned it27- Known integrations and credentials (then treat the list as incomplete on28 principle — the inventory step hunts for the rest)29…
Excerpt shown under the repository's MIT license.
More skills in pm-claude-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
