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 agentmods add commands/vaibhavaher100/wrap-session/unwrapgit clone --depth 1 https://github.com/VaibhavAher100/wrap-sessionWrote 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/vaibhavaher100/wrap-session/unwrap)<a href="https://agentmods.dev/commands/vaibhavaher100/wrap-session/unwrap"><img src="https://agentmods.dev/badge/commands/vaibhavaher100/wrap-session/unwrap.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00740 |
| Opus 5 | $0.00000 | $0.00370 |
| Sonnet 5 | $0.00000 | $0.00148 |
| Haiku 4.5 | $0.00000 | $0.00074 |
Grade A, and why
unwrap 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 4d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are resuming a Claude Code session. Execute all steps below in order — no confirmation needed.
Step 0 — Validate logs/state.md
Use the Bash tool:
head -1 logs/state.md 2>/dev/null && wc -c < logs/state.md 2>/dev/null
- If file is missing or empty: output
> [!warning] logs/state.md is missing or empty. Session state is unavailable. Proceed with caution — open items and in-progress work cannot be loaded.then continue with Steps 2-4 as best you can. - If first line is not
---: output> [!warning] logs/state.md appears malformed (does not start with YAML frontmatter). The file may have been written incorrectly. Content below may be unreliable.then continue. - If valid: proceed silently.
Step 1 — Read current state
Read logs/state.md in full.
Step 2 — Find and read latest session log
Use the Bash tool to find the most recent session file:
ls logs/sessions/*.md 2>/dev/null | sort | tail -1
Read that file in full.
Step 3 — Output structured briefing
Check the confidence field from the session frontmatter first:
- If
confidence: low— prepend a warning block before the briefing (see format below) - If
confidenceis absent — note(pre-schema, confidence unknown) - If
confidence: medium— note it inline, no separate warning needed
Output the briefing in this exact format:
## Session Resumed
**Last session:** <session-id> (<session-date>)
**Summary:** <summary from frontmatter>
**Confidence:** <value> <— if low, see warning above>
### What was in progress
<In Progress section from logs/state.md — or "Nothing" if empty>
### Open items
<Open Items section from logs/state.md, preserving [carried N] tags>
### Health
<one-line status from Health in logs/state.md>
### Active decisions (last 3)
<Last 3 entries from logs/decisions.md — title + Chose line only>
Low confidence warning format (prepend before briefing):
> [!warning] Low-confidence session log
> The previous session (`<session-id>`) was logged with **low confidence** — compaction occurred and early context was lost. Key actions or decisions may be missing from the log. Do not rely on the session log as a complete record. Cross-check with `logs/state.md` and `logs/decisions.md` before resuming work.
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.
- 4d ago First seen · 88 lines · 0 tokens per session scan A 178b833fbb0b
unwrap is a command published in the GitHub repository VaibhavAher100/wrap-session (1 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 740 tokens. 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
ask
Ask a peer session a question and wait for its answer.
monitor
Open the read-only web view of peers, threads and bus health.
register
Register this project directory as a named bridger peer.
send
Send a message to a peer session.
status
Show bridger identity, peers, and unread message counts.
notes
Maintain the ROOM BRAIN — the structured state file the coach reasons from.