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 skills add jeanfbrito/rocket-cli --skill rocket-findgit clone --depth 1 https://github.com/jeanfbrito/rocket-cliWrote 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/jeanfbrito/rocket-cli/rocket-find)<a href="https://agentmods.dev/skills/jeanfbrito/rocket-cli/rocket-find"><img src="https://agentmods.dev/badge/skills/jeanfbrito/rocket-cli/rocket-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/skills/jeanfbrito/rocket-cli/rocket-find"><img src="https://agentmods.dev/badge/skills/jeanfbrito/rocket-cli/rocket-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 | $0.00119 | $0.00847 |
| Opus 5.5 | $0.00048 | $0.00339 |
| Sonnet 5.5 | $0.00024 | $0.00169 |
| Haiku 4.5 | $0.00012 | $0.00085 |
Grade A, and why
rocket-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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rocket-find
Locate a known-ish message across rooms. Local full-text first; server fallback only when scoped to a room.
Transport
- Prefer MCP when connected:
search_messages, thenget_message_contextto expand a hit. - Otherwise shell out:
rocket-cli search <query> --json(add--room <room>to scope),rocket-cli context <messageId> --json. - Multi-server:
--profile <name>(CLI) orROCKET_CLI_PROFILE(MCP env).
Search semantics (FTS5 — important)
- Query terms are split on whitespace and ANDed together — every term must appear. Fewer, more distinctive terms beat a long phrase.
- A trailing
*on a term is a prefix match (deploy*matches deploy/deployed/deployment). Use it when the user gives a stem. - Operators like
AND/OR/NOT/NEARand punctuation are treated as literal text, not syntax — you can't compose boolean queries; pick good terms instead. - Cross-room search is local-only. Without a
room, search runs purely over the local FTS cache across ALL cached rooms (instant, no network). The server fallback (which reaches uncached history) fires ONLY when you pass aroomAND local hits are thin.
Workflow
- Run a cross-room search first.
search_messagesparams:query(required),room(optional),author(optional username filter),limit(1-100, default 20). Start withoutroomso all cached rooms are covered. Choose 1-3 distinctive terms from the user's ask; add a trailing*to stems. - Read the result envelope. It carries each hit's
snippetand asource(localorserver), pluslocalOnlyand an optionalnoteexplaining thin or degraded results. - If hits are thin AND the user implies a room, re-run scoped to that room (
room: "#whatever") to engage the server-side fallback that reaches uncached history. If the user gave no room hint and results are thin, tell them cross-room search is cache-only and offer to scope to a likely room (which enables server search there). - Use
authorwhen the user says "who said X" or "find what posted about Y" — filter by their username. - Present hits ranked, each with: room, author, the snippet, and the permalink. Keep it scannable.
- Offer to expand. "Want the conversation around that one?" →
get_message_context(params:messageId— a hit's id or a pasted link;before0-50 default 10;after0-50 default 5). A thread reply pivots to its whole thread automatically.
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 · 38 lines · 119 tokens per session scan A f912e54cfb7e
rocket-find is a skill published in the GitHub repository jeanfbrito/rocket-cli (3 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 847 once invoked, about $0.0005 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…