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 jerseycheese/agent-skills --skill wrap-it-upgit clone --depth 1 https://github.com/jerseycheese/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/jerseycheese/agent-skills/wrap-it-up)<a href="https://agentmods.dev/skills/jerseycheese/agent-skills/wrap-it-up"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/wrap-it-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/jerseycheese/agent-skills/wrap-it-up"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/wrap-it-up.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 | $0.00119 | $0.01607 |
| Opus 5 | $0.00060 | $0.00804 |
| Sonnet 5 | $0.00024 | $0.00321 |
| Haiku 4.5 | $0.00012 | $0.00161 |
Grade A, and why
wrap-it-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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wrap-it-up
Purpose
End-of-chat closure ritual. Two jobs: (1) produce a short closing report so the conversation has a clean outcome, and (2) sweep the current project's durable context files — memory, status docs, tasks, plans, and any project-specific reminders — so anything worth keeping makes it out of the transcript, and clear the chat's runtime leftovers (stop dev servers it started, delete its finished plan files) before the chat ends.
This skill is project-aware. It adapts to whatever repo you run it from: it discovers the context files the current project actually uses instead of assuming a fixed layout, and it honors any end-of-session conventions documented in that project's CLAUDE.md / AGENTS.md. Run it from a code repo and it sweeps that repo's docs and tasks; run it from a personal life-OS or notes repo and it picks up that repo's own conventions.
What to produce
A short closing report with three parts. Keep it tight — colleague-over-coffee tone, not a meeting recap.
- Summary — 3–6 bullets of what was actually accomplished. Outcomes, not narration.
- Decisions — anything we decided that future-me will need to know. One bullet each.
- Loose ends — anything left unfinished, with a one-line next step. If there are none, say so.
If the chat was mostly exploration with no concrete output, say that. Don't fabricate accomplishments.
Merged PRs — run post-merge first
Before the housekeeping sweep, check whether any PR opened or referenced in this chat merged during the session (ask if genuinely unclear, but take the user's own "merged"/"PR is merged" statement as ground truth per their global CLAUDE.md — don't re-verify it). If one did, run the post-merge skill for it FIRST, automatically, no confirmation — it syncs the base branch, deletes the merged branch + worktree, closes the linked issue, and scores the next issue. Fold its outcome into this closure's summary rather than leaving it as a loose end for a future chat to remember to run. Only skip it if post-merge already ran earlier in this same chat for that PR.
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 · 94 lines · 119 tokens per session scan A 733b87c0df35
wrap-it-up is a skill published in the GitHub repository jerseycheese/agent-skills (1 stars, last pushed 8d ago), licensed MIT. It adds 119 tokens to every session and 1,607 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
pneuma-preferences
Persistent user preference memory across sessions. Consult this skill BEFORE making any design, style, or aesthetic decisions — choosing colors, themes, layouts, fonts, tone of voice, content density, or visual direction. Also consult when starting a new creative task in any mode, when the user corrects your style…
ucai-patterns
Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.
knowledge-base
Retrieves and updates project-specific prompt knowledge from comparison evidence and user feedback. Use only for prompt analysis or post-comparison learning within a Rashomon evaluation.
orient
Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and…
memory
Use when user invokes /memory with a subcommand (search, trace, add, episode, status). Also triggers on "search my memory for X", "add to memory", "what do I know about X" (when membrain is available), "memory status", "memory trace". Searches and manages the membrain knowledge graph via MCP tools or HTTP API.
capture
Use when user invokes /capture to capture information from the current conversation into a staging file for later reflection and knowledge graph processing. Accepts no arguments (auto-extract), specific facts as text, or filter keywords like "decisions" or "technical". Do NOT use when the user wants to write directly…