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/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/wrap-find)<a href="https://agentmods.dev/commands/vaibhavaher100/wrap-session/wrap-find"><img src="https://agentmods.dev/badge/commands/vaibhavaher100/wrap-session/wrap-find/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/vaibhavaher100/wrap-session/wrap-find"><img src="https://agentmods.dev/badge/commands/vaibhavaher100/wrap-session/wrap-find.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 | $0.00000 | $0.00371 |
| Opus 5.5 | $0.00000 | $0.00148 |
| Sonnet 5.5 | $0.00000 | $0.00074 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
wrap-find scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Search session logs for a keyword or phrase. The search term is everything after /wrap-find in the user's message.
Execute immediately, no confirmation needed.
Step 1 — Run the search
Assign the user's search term to a shell variable and pass it as data — do not interpolate it directly into the grep pattern string. Use -F (fixed strings) to prevent regex interpretation of the term.
Use the Bash tool:
SEARCH_TERM='<SEARCH_TERM>'
grep -riFl -- "$SEARCH_TERM" logs/sessions/ 2>/dev/null | sort
Replace <SEARCH_TERM> with the user's argument when setting the variable. If the term contains single quotes, use double quotes around the assignment instead.
Step 2 — For each matching file
Read only the frontmatter of each matching file to get session_id, session_date, and summary.
Then run a second grep to extract the matching lines with context:
SEARCH_TERM='<SEARCH_TERM>'
grep -inF -- "$SEARCH_TERM" <FILE> 2>/dev/null
Step 3 — Output results
For each matching session, output:
### <session-id> (<session-date>)
<summary>
Matches:
- Line N: <matching line>
- Line N: <matching line>
Separate each session result with a horizontal rule.
If no matches found, output: No sessions found matching "<SEARCH_TERM>".
After all results, print: Found in N of M sessions.
Notes
- Search is case-insensitive, fixed-string (no regex)
- Searches full file content — frontmatter, actions table, reasoning, open items
- For tag search, user can pass e.g.
careerorembeddedto match topic tags
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 · 52 lines · 0 tokens per session scan A ef5e94e066a1
wrap-find is a command published in the GitHub repository VaibhavAher100/wrap-session (1 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 371 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
notes
Maintain the ROOM BRAIN — the structured state file the coach reasons from.
handoff
Fast session handover — capture current state and write a resume command for the next session. Use when context is filling up or you need to switch tasks.
wrap-up
End-of-session protocol — capture decisions, constraints, learnings, and next-session task; create a session snapshot before context is lost.
retrieve
Full-text search persistent memory (BM25) and present results grouped by category — decisions, constraints, learnings, tasks.
create
Capture current session context to docs/handoff/HANDOFF.md.
session-memory
Maintain context and learnings across Claude Code sessions for continuous improvement.