shutdown-dev

A shutdown procedure for ending a development teammate's session while preserving enough context for someone else to continue.

In plain words
What is it for?
It helps check task and worktree status, request a written handoff, get approval, and verify that the teammate's process has stopped.
Why use it?
It prevents unfinished work, uncommitted changes, and useful session knowledge from being lost when a teammate is rotated out.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/loopdive/js2/shutdown-dev
Any agent
npx skills add loopdive/js2 --skill shutdown-dev
Clone the repo
git clone --depth 1 https://github.com/loopdive/js2

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,355 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.01355
Opus 5 $0.00024 $0.00678
Sonnet 5 $0.00010 $0.00271
Haiku 4.5 $0.00005 $0.00136

Measured yesterday against content hash d49a51bb3684, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shutdown-dev 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 yesterday.

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.

.claude/skills/shutdown-dev/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shutdown Dev

Gracefully terminate a dev teammate's session while preserving their working context for future resumption.

When to use

  • Team scale-down (e.g. going from 8 → 6 devs after OOM pressure or sprint close)
  • Dev assigned to an orphaned branch after their PR was closed
  • Sprint retrospective and wrap-up — shutting down devs between sprints
  • Memory pressure requiring you to shed agent processes

Pre-shutdown checklist

  1. Is the dev in the middle of something? Check their task status:

    # via TaskList, filter for owner == <dev-name>
    

    If they're mid-implementation on a non-trivial task, prefer rotating them OFF that task first rather than losing the work.

  2. Is the user currently talking to this dev? If yes, confirm with the user before shutting down.

  3. Do they have uncommitted work in their worktree? Check via their file-locks entries and any in-flight PRs. Warn them to commit before approving shutdown.

Step 1: Send the shutdown_request

SendMessage to: <dev-name>
Type: shutdown_request

{"type": "shutdown_request", "reason": "<reason — e.g. 'Scaling team from 8 to 6 after OOM recovery; your current PR is merged/closed and you have no active task'>. Before approving shutdown: (1) write your working context to plan/agent-context/<dev-name>.md — include active branches, any in-progress thoughts, and anything a successor agent would need to resume. Keep it concise (~100 lines). (2) Commit any uncommitted WIP in your worktrees, or note explicitly that nothing is WIP. (3) Reply with shutdown_response approve=true. Your worktrees and branches stay — another dev can resume them later."}

Critical constraints in the message:

  • MUST instruct them to write plan/agent-context/<name>.md FIRST
  • MUST tell them to commit uncommitted WIP
  • MUST NOT ask them to narrate their context in the chat reply (that bloats the tech lead's context)
  • Reply should be a one-line shutdown_response approve=true

Step 2: Wait for response

Read the full file on GitHub · 134 lines

Changes

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.

  1. yesterday First seen · 134 lines · 48 tokens per session scan A d49a51bb3684

Subscribe to this mod's changes

shutdown-dev is a skill published in the GitHub repository loopdive/js2 (59 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 1,355 once invoked, about $0.0002 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 2026-08-30.