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.
git clone --depth 1 https://github.com/hautc-it/cilWrote 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/commands/hautc-it/cil/wrap-up)<a href="https://agentmods.dev/commands/hautc-it/cil/wrap-up"><img src="https://agentmods.dev/badge/commands/hautc-it/cil/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/commands/hautc-it/cil/wrap-up"><img src="https://agentmods.dev/badge/commands/hautc-it/cil/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 | $0.00027 | $0.00381 |
| Opus 5.5 | $0.00011 | $0.00152 |
| Sonnet 5.5 | $0.00005 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
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.
What it actually says
/wrap-up
End-of-session protocol. Capture learnings before context is lost.
Step 1 — Summarize
What was accomplished this session? One paragraph, factual.
Step 2 — Capture learnings
For each insight from this session:
Questions to ask:
- What worked well and should be repeated?
- What was surprising, wrong, or unexpected?
- What would you do differently next time?
- What constraints were discovered?
Store each learning:
memory_store("learning", "[the insight]", ["relevant", "tags"])
What to store: decisions, constraints, architecture facts, discovered limitations, patterns that worked. Do NOT store: build errors, compile warnings, temporary bugs fixed during the session, tool output logs.
Step 3 — Capture decisions
For each architecture or design decision made:
memory_store("decision", "[what was decided] — [why]", ["component", "area"])
Step 4 — Capture constraints
For any constraint discovered (performance limits, API quirks, team rules):
memory_store("constraint", "[the constraint and where it applies]", ["area"])
Step 5 — Plan next session
- What is unfinished?
- What is the first task to pick up next time?
Store as task:
memory_store("task", "[next task description]", ["next-session"])
Step 6 — Housekeeping
git status
Flag any uncommitted work. Don't leave things dangling.
Create session snapshot:
session_snapshot("[session summary in 1-2 sentences]", ["decision1", "decision2"])
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 · 81 lines · 27 tokens per session scan A 170078b72480
wrap-up is a command published in the GitHub repository hautc-it/cil (1 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 381 once invoked, about $0.0001 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 commands, from other repositories
unwrap
You are resuming a Claude Code session. Execute all steps below in order — no confirmation needed.
wrap-find
Search session logs for a keyword or phrase. The search term is everything after /wrap-find in the user's message.
claudikins-automatic-context-manager:manual-handoff
Manually trigger context handoff - skip waiting for 60% threshold.
claude-flow-memory
Interact with Claude-Flow memory system.
session-memory
Maintain context and learnings across Claude Code sessions for continuous improvement.
memory-manager
Knowledge management with Memory tools for persistent insights.