Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/wyre-ai/msp-claude-plugins/offboard-usergit clone --depth 1 https://github.com/WYRE-AI/msp-claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/offboard-user)<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/offboard-user"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/offboard-user.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00027 | $0.00606 |
| Opus 5 | $0.00014 | $0.00303 |
| Sonnet 5 | $0.00005 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
offboard-user scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offboard CIPP User
Delegate to the user-offboarding-runner agent. The agent handles the full sequence: tenant + user resolution, audit-state capture, account lock, mailbox handling, license reclaim, and structured offboarding record output.
Arguments
user(required) — UPN or display name of the user being offboardedtenant(optional) — Tenant default domain or display name (skip if user is unique across all tenants)posture(optional) — standard, termination, or contractor — controls action ordering and defaults (defaults to standard)mailbox-action(optional) — shared, forward, archive, or hold — what to do with the mailbox (defaults to shared)forward-to(optional) — UPN to forward mail to (defaults to user's manager if set in M365)dry-run(optional) — Show every action that would be taken without executing (true/false)
Posture defaults
| Posture | Action ordering | Mailbox default | Confirmation depth |
|---|---|---|---|
standard |
Audit first → disable | Convert to shared | One confirmation before destructive sequence |
termination |
Disable + revoke + reset MFA first → audit second | Convert to shared | Single combined confirmation; speed-first |
contractor |
Audit first → disable | Archive (no shared conversion) | One confirmation; no forwarding by default |
What the workflow does
- Resolve tenant via
cipp_list_tenantsand user viacipp_list_users - Confirm the match with the requester
- Capture audit state:
cipp_list_user_groups,cipp_list_user_devices,cipp_list_mailbox_permissions - Run
cipp_offboard_userwith options derived frompostureandmailbox-action - (If forwarding requested) verify
cipp_set_email_forwardingwas applied - (If OOO requested) set
cipp_set_out_of_office - Produce a structured offboarding record for the ticket
Manual steps the agent will flag
CIPP doesn't handle these — the agent surfaces them in the final record:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 47 lines · 27 tokens per session scan A 9097da89d9d1
offboard-user is a command published in the GitHub repository WYRE-AI/msp-claude-plugins (44 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 606 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other commands, from other repositories
project
프로젝트 초기화 단일 진입점 — 소크라테스 인터뷰 후 커스텀 에이전트·스킬 체인·AGENTS.md 생성. update/evolve/doctor 하위 모드 지원.
resume_handoff
Resume work from handoff document with context analysis and validation.
factory
Run one pass of the ticket queue — scan the tracker for human-authorized tickets, claim one, and route it to the right workflow (spec a raw ticket, groom the backlog, hunt a bug, or build an approved spec in its own worktree via /sonu:build). You are the trigger; there is no daemon. Never merges and never authorizes…
list
Show the project backlog (open items by default, sorted by priority then age). Ask for --all, --sort date or --priority high and Claude re-runs the engine with them.
prune
Delete old closed entries (status done/cancelled) left over from earlier plugin versions. Shows the list first; the deletion itself asks for your approval.
add
Add a task to the backlog manually. Use when the user explicitly asks to record something in the backlog.