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/michaeljauk/brain-starternpx agentmods add skills/michaeljauk/brain-starter/wrap-session-upWrote 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/michaeljauk/brain-starter/wrap-session-up)<a href="https://agentmods.dev/skills/michaeljauk/brain-starter/wrap-session-up"><img src="https://agentmods.dev/badge/skills/michaeljauk/brain-starter/wrap-session-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/michaeljauk/brain-starter/wrap-session-up"><img src="https://agentmods.dev/badge/skills/michaeljauk/brain-starter/wrap-session-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 | $0.00060 | $0.02633 |
| Opus 5.5 | $0.00024 | $0.01053 |
| Sonnet 5.5 | $0.00012 | $0.00527 |
| Haiku 4.5 | $0.00006 | $0.00263 |
Grade A, and why
wrap-session-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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wrap Session Up
End-of-conversation review skill. Replays the current Claude Code session, identifies what was accomplished, what's still open, and documents everything in the right places before the context is lost.
Trigger phrases
/wrap-session-up- "wrap up this session"
- "anything left open?"
- "let's wrap up"
Step-by-step workflow
1. Replay the session
Review the full conversation history. Extract:
- What was accomplished — files created/edited, commands run, problems solved
- Open action items — things discussed but not yet done, commitments made ("I'll do that later", "next step is..."), tasks the user mentioned wanting to do
- Decisions made — technology choices, architecture decisions, approach changes
- New knowledge surfaced — things learned about the project, codebase, or tools that should be persisted
- Files touched — all files created or modified during the session
- Friction points — anything that caused repeated correction, workarounds, or user frustration (skill misbehaved, tool returned wrong output, Claude misunderstood something repeatedly, a convention was unclear). Only log if it happened more than once or was explicitly called out.
Run git diff --stat to get a concrete picture of what changed.
2. Check for loose ends
For each open item identified, check if it was resolved later in the session or if it's genuinely still open. Common patterns:
- User said "I'll handle X" → still open, needs tracking
- User asked to do X but conversation moved on → still open
- A TODO/FIXME was added in code → still open
- An error was hit but not fully resolved → still open
- User mentioned wanting to follow up on something → still open
Also check for:
- Uncommitted changes —
git statusandgit diff --statto see what changed - Unfinished edits — files partially modified
- Broken state — tests failing, build errors introduced
3. Cross-reference action items
For each open item, check if it's already tracked:
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 · 261 lines · 60 tokens per session scan A e8ac2a3b22fb
wrap-session-up is a skill published in the GitHub repository michaeljauk/brain-starter (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 2,633 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
vault-onboarding-guide
An interactive guide for learning a file-based knowledge store with an agent. It teaches how to organize incoming material, projects, plans, tasks, logs, parked work, and resumed work.
brain
Orient in the user's big-brain second brain and work brain-aware for the rest of the session. Use when the user types /brain, or asks "what am I working on", "what's on my plate", "catch me up", "what's overdue", or at the start of a session about ongoing work. Loads the vault overview, reports it in one screen, and…
obsidian-ai-setup
Bootstrap an Obsidian vault with the AI Pro Obsidian Plugin. Creates the complete vault structure, system files, Obsidian configuration, memory system, hooks, and output styles, then runs personalized onboarding to tailor the workspace to the user. Uses a single universal structure with no mode selection. Trigger when…
alive-morning
Morning briefing -- read all walnut states, surface priorities, inbox count, stale walnuts, people nudges.
priority-dashboard
Use this to rebuild, inspect, or temporarily steer {{username}}'s current PersonalOS priority dashboard from canonical Actions, Attention Triggers, and owner context. Do NOT use it to create, complete, or independently manage tasks; use task-manager for Action and Trigger lifecycle changes.
screenpipe-api
Query the user's local and synced-device data via the screenpipe REST API at localhost:3030 — recordings, audio, UI, meetings, connected services, and memory. Use for screen activity, other-device or cross-device history, productivity, media export, connections, durable memory, or discovering and automating saved…