Borrowing it
Nothing to install: this file belongs to white1024/agent-nextup. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/white1024/agent-nextup/main/.claude/skills/wrap-up/SKILL.mdgit clone --depth 1 https://github.com/white1024/agent-nextupWrote 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/white1024/agent-nextup/wrap-up)<a href="https://agentmods.dev/skills/white1024/agent-nextup/wrap-up"><img src="https://agentmods.dev/badge/skills/white1024/agent-nextup/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/white1024/agent-nextup/wrap-up"><img src="https://agentmods.dev/badge/skills/white1024/agent-nextup/wrap-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 | $0.00053 | $0.00772 |
| Opus 5.5 | $0.00021 | $0.00309 |
| Sonnet 5.5 | $0.00011 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wrap-up — closing a session
Goal: the next session should be able to pick up seamlessly by reading nothing more than the project's entry point (CLAUDE.md and whatever it points at).
Step 0: read CLAUDE.md at the project root (or the equivalent entry document) and work out what each step below means in this project — the commit conventions, the health-check command, where progress and decisions are recorded. Where the entry document says nothing, fall back to the generic default in each step. Then run through them in order:
1. Take stock of the working tree and commit
- Survey with
git status. If there are uncommitted changes, commit them in batches by logical sub-task rather than all at once. - A message is motivation (why) plus technical reasoning (how), not a list of files. Where the project has its own commit conventions — message format, sign-off, environment traps — follow those.
2. Health check
If the project has a health-check command (doctor, lint, tests — check the entry document or the development docs), run it. It must come back clean; fix it before wrapping up if it does not.
3. Take stock of verification (be honest)
Sort everything this session claims to have finished:
- Verified: with evidence — what you ran, what you saw (tests green, real output).
- Unverified: with the method — who could verify it and by what steps (for example the parts needing manual GUI operation).
- Anything you are unsure about counts as unverified. Do not fake it.
4. Write back into the project's record
Add this session's progress, the decisions that were settled and the pitfalls you hit to the project's own record mechanism (a progress log, a decision record, memory, task state — whichever exists). Where the project provides tools for recording, use the tools rather than editing files by hand.
The discipline: every fact goes into its own source of truth and is not copied to a second place — in particular, do not push current state or decisions back into an index or entry file such as CLAUDE.md.
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.
- 1mo ago First seen · 47 lines · 53 tokens per session scan A a413321e8029
wrap-up is a skill published in the GitHub repository white1024/agent-nextup (2 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 772 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 2026-08-31.
Other skills, from other repositories
nav-compact
Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
Promote
Take a slice of the current conversation and promote it to a durable vault artifact — concept note, project update, person profile, or doctrine entry. Pairs with /close. /close writes the daily note (transient outcome record); /promote elevates specific insights to permanent vault content the framework can refer back…
open
Boot the session, load context from the vault, and surface what matters.
using-discussion
Silently persist and recover visible multi-turn clarification, interviews, design Q/A and brainstorming, regardless of which Skill or prompt starts them. Use for ongoing discussion, not ordinary single-answer chat.
capsule-compact
Compact a long capsule chain. Walks parentcapsuleid backward from a head capsule; if chain >= 5, summarizes oldest 3 into a chain-summary capsule. Manual invocation.