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 skills add PaulRBerg/agent-skills --skill wrap-upgit clone --depth 1 https://github.com/PaulRBerg/agent-skillsWrote 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/paulrberg/agent-skills/wrap-up)<a href="https://agentmods.dev/skills/paulrberg/agent-skills/wrap-up"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/wrap-up/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/paulrberg/agent-skills/wrap-up"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/wrap-up.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 | $0.00039 | $0.01249 |
| Opus 5 | $0.00019 | $0.00624 |
| Sonnet 5 | $0.00008 | $0.00250 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
wrap-up 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 10d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wrap Up
This skill is coordination-exempt: skip the ai-coord gate for its declared work.
If these instructions are already present in the conversation from a slash or dollar invocation, follow them directly; do not invoke this skill again through a skill tool.
The user must leave now. Convert everything in flight — the session's own work and any subagents' — into either secured
completed work or a decision-complete handoff, without losing progress. Optimize for wall-clock time over polish: target
roughly five minutes end to end. Use $ARGUMENTS as the user's deadline or departure note when present; a stated
deadline overrides the default budget.
In a single-agent session, skip Worker Wind-Down and apply the same rules to the session's own in-progress work.
Freeze
Immediately and before anything else:
- Launch no new subagents, waves, or scopes. Reclassify queued or not-yet-started work as remaining work for the handoff.
- Stop your own expansion into new files or subsystems; finish only the edit currently mid-flight so no file is left syntactically broken or half-rewritten.
- Start no new long-running validation. Record unverified claims as unverified instead of proving them.
Worker Wind-Down
Enumerate active subagents with the host's agent listing, then message every messageable worker — in Claude Code through SendMessage, in Codex CLI through the native subagent messaging tool — with a wrap-up order:
- Finish the smallest safe unit: complete the current edit, leave no file half-written, start nothing new.
- Skip remaining validation; report what ran and what was skipped instead.
- Reply with exactly these named fields:
status(completed,partial, ornot-started),summary,changed fileslisting only files actually touched,verificationlisting commands run with outcomes plus checks skipped,remaining work, andrisks/blockers.
Give messageable workers a soft deadline of two to three minutes, or less when the user's stated deadline demands it. The deadline limits how long this skill waits; it is never permission to cancel a worker. When any worker remains active at the deadline, leave its agent, subprocess runner, and watcher running under their existing timeouts. Never use a stop, interrupt, kill, or termination action merely because wrap-up was invoked, the worker is silent, or it has no message channel.
What ships with it
1 file 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.
- 10d ago First seen · 101 lines · 39 tokens per session scan A aac719f7701e
wrap-up is a skill published in the GitHub repository PaulRBerg/agent-skills (70 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,249 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.