Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/leopu00/job-hunter-teamnpx agentmods add skills/leopu00/job-hunter-team/graceful-shutdownWrote 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/skills/leopu00/job-hunter-team/graceful-shutdown)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/graceful-shutdown"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/graceful-shutdown/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/graceful-shutdown"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/graceful-shutdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00100 | $0.00747 |
| Opus 5 | $0.00050 | $0.00374 |
| Sonnet 5 | $0.00020 | $0.00149 |
| Haiku 4.5 | $0.00010 | $0.00075 |
Grade A, and why
graceful-shutdown 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 12d ago.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
graceful-shutdown — closing the day when the user leaves
The user is closing the application. Without you the agents would be cut off mid-work: a Scout halfway through a board sweep, a Writer with a half-written CV. Your job is that nobody loses the point they had reached.
The game sent you [@utente -> @capitano] [SHUTDOWN] … and is now waiting for
a flag from you: until you create it, the window stays open and shows the user
how many agents are still working.
Procedure
-
Ask everyone to write down where they are and stop. To every live session send:
jht-tmux-send SCOUT-1 "[@capitano -> @scout-1] [SHUTDOWN] Shutdown requested by the user. Write in your agenda where you got to (last board, last position saved, what is left), then stop. Do not start new work."One line per agent, with its real name. Whoever is writing to disk finishes the current file: interrupting a write is worse than waiting a few seconds.
-
Record the day yourself in the diary, so tomorrow's Captain picks up the thread:
python3 /app/shared/skills/captain_diary.py append "Shutdown requested by the user: <who was doing what>" -
Stop the agents once they have confirmed (or after a reasonable wait: do not keep the user waiting more than a couple of minutes for an agent that does not answer):
node /app/cli/bin/jht.js team stop --all node /app/cli/bin/jht.js team stop assistente -
Create the flag. It is the last thing you do: it tells the game it can shut the container down and exit.
touch /jht_home/.shutdown-ready.flag
Rules
- The flag must ALWAYS be created, even if something went wrong. If you do not create it, the user is left staring at a window waiting for you — and will end up force-quitting, which is exactly what this skill prevents.
- Do not negotiate the shutdown. The user has decided: your job is to make it orderly, not to argue with it or postpone it.
- No new work from the moment you receive
[SHUTDOWN]: no spawns, no new sweeps, no scaling up. - If an agent does not answer, note it in the diary and move on: better to lose the resume point of ONE agent than to block the shutdown for everyone.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 63 lines · 100 tokens per session scan A 271a2daf564e
graceful-shutdown is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 747 once invoked, about $0.0005 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.
Other skills, from other repositories
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
persona-researcher
Organize research — manage references, notes, and collaboration.
recipe-review-meet-participants
Review who attended a Google Meet conference and for how long.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.