Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add atretyak1985/swarmery/plugin install coreWrote 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/atretyak1985/swarmery/session-closeout)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/session-closeout"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/session-closeout/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/atretyak1985/swarmery/session-closeout"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/session-closeout.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00047 | $0.00924 |
| Opus 5.5 | $0.00019 | $0.00370 |
| Sonnet 5.5 | $0.00009 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
session-closeout 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 25d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Closing artifacts are how finished work becomes visible: the dashboard reads
SUMMARY.md, and the retro/advisor loop ingests phases/09-retrospective.md
and the delegation ledger. A task closed without them is invisible work.
What to write
{task-dir}/SUMMARY.md(canonical final report, ≤300 lines) — exactly these seven sections:## Результат,## Змінені файли,## Агенти,## Сесії,## Відхилення від плану,## Скріншоти,## Follow-ups. Deviations compare actual agents/loops against ORCHESTRATION.md, not only the plan; the screenshots section lists{task-dir}/screenshots/files with captions or states "None captured". Format details:resources/summary-format.md.{task-dir}/phases/09-retrospective.md(≤150 lines) — for non-trivial tasks. MUST use the machine-parsed headings:## Lessons Learnedwith### Lesson N: <title>subsections each carrying a**Action**: …line, and## Process Improvements(that exact heading — the ingester regexes match it, not synonyms). Read{task-dir}/logs/agents.md(7-cell ledger) first — its quality/mistakes cells are the evidence base. Format:resources/retrospective-format.md.{task-dir}/plan/SUMMARY.md(≤120 lines) — for plan-driven tasks: the plain-language overview the dashboard shows at the top of the plan's Summary tab, above the per-phase reports. Written for the operator, not for an engineer: what the task was in plain words, what was built and how it works, where to see it, the headline numbers, what is left and what the operator has to do. No commit hashes or file paths in the body. Format:resources/plan-summary-format.md.- Archive when every criterion is met:
bash "${CLAUDE_PLUGIN_ROOT}/bin/agent-work.sh" complete {task-id}. Never archive with unmet criteria or a missing SUMMARY.md — escalate instead.
Honesty rule: outcome is Success | Partial | Failed as it actually was;
lessons cite specific phases/files; a flattering retro poisons the
self-improvement loop.
What ships with it
3 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.
- 25d ago Changed · +7 lines 382a395d1cf2
- 1mo ago First seen · 59 lines · 47 tokens per session scan A e787506462db
session-closeout is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 924 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
execute
Execute phase — wave-based crew dispatch with critic gates and evidence-based verification.
recipe-batch-invite-to-event
Add a list of attendees to an existing Google Calendar event and send notifications.
recipe-block-focus-time
Create recurring focus time blocks on Google Calendar to protect deep work hours.
recipe-create-shared-drive
Create a Google Shared Drive and add members with appropriate roles.
recipe-find-free-time
Query Google Calendar free/busy status for multiple users to find a meeting slot.
recipe-organize-drive-folder
Create a Google Drive folder structure and move files into the right locations.