Borrowing it
Nothing to install: this file belongs to lbruton/claude-context. 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/lbruton/claude-context/master/.agents/skills/wrap/SKILL.mdgit clone --depth 1 https://github.com/lbruton/claude-contextWrote 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/lbruton/claude-context/wrap)<a href="https://agentmods.dev/skills/lbruton/claude-context/wrap"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/wrap/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/lbruton/claude-context/wrap"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/wrap.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 | $0.00097 | $0.03953 |
| Opus 5.5 | $0.00039 | $0.01581 |
| Sonnet 5.5 | $0.00019 | $0.00791 |
| Haiku 4.5 | $0.00010 | $0.00395 |
Grade A, and why
wrap 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 5d 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wrap Session
End-of-session orchestrator. Run the entire flow autonomously without asking the user
for permission between steps. The user invoked /wrap once — that is the permission.
Recommended end-of-session flow
With PR merged this session: /pr-cleanup → /wrap
Without PR: /wrap
Quick re-orient only: /start (no wrap needed)
/retro was retired in DEVS-75 (2026-09-27): its mem0 retro-learning entries were never
read back by any session. Lessons now go to each harness's local memory, which it loads.
Arguments
- --handoff: Pass
--handoffif work continues in a new terminal. Adds the handoff fields (continue issue ID, first action, gotchas) to the Step 3 session summary.
Design Principle (read this first — it governs everything below)
Each memory layer has one job (DEVS-75, confirmed by the user 2026-09-27):
| Layer | Holds | Written by /wrap as |
|---|---|---|
| mem0 | The bigger picture: what was worked on, when, where, and what was decided | ONE detailed session summary (Step 3) |
Local agent memory (Claude Code: auto-memory; Codex: ~/.codex/memories/) |
Active day-to-day operating memory: preferences, corrections, gotchas | Local memory entries (Step 4) |
.context/ |
Long-term foundational context for implementation work | Doc sync via chore PR (Step 5) |
| SessionFlow + git | Verbatim turns and exact history | Nothing — indexed automatically |
mem0 + SessionFlow + git history together give the full picture. mem0 does not need to repeat turn-level detail — it needs searchable anchors (issue IDs, file paths, PR numbers, decisions) that let a later session find the right SessionFlow turns and commits.
Three rules that follow from this:
- Run the whole flow in one shot. No "STOP HERE", no "wait for user acknowledgment", no phase banners. Just observe → summarize → save → report.
- Take action autonomously where the action is obvious. If main is behind origin and the working tree is clean, pull — do not ask. If a worktree has uncommitted changes, do not delete it and do not ask — just report it as a soft warning.
- All warnings live in the Session Health block at the end. Never interrupt the flow with a yellow/red issue mid-stream. Report once, at the bottom, in one place.
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.
- 5d ago Changed 665c84b91d78
- 9d ago Changed 6e5204cb1138
- 11d ago First seen · 351 lines · 97 tokens per session scan A c0a38dbed84d
wrap is a skill published in the GitHub repository lbruton/claude-context (2 stars, last pushed 5d ago), licensed MIT. It adds 97 tokens to every session and 3,953 once invoked, about $0.0004 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 2026-10-17.
Other skills, from other repositories
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
Migrate
Intakes external content (notes, CLAUDE.md, Cursor rules, Obsidian/Notion/Apple Notes exports), classifies chunks against the LifeOS taxonomy, and commits with provenance after confidence-tiered approval. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import…
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.