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 vlinx-io/VelaTerm --skill vsearchgit clone --depth 1 https://github.com/vlinx-io/VelaTermWrote 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/vlinx-io/velaterm/vsearch)<a href="https://agentmods.dev/skills/vlinx-io/velaterm/vsearch"><img src="https://agentmods.dev/badge/skills/vlinx-io/velaterm/vsearch/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/vlinx-io/velaterm/vsearch"><img src="https://agentmods.dev/badge/skills/vlinx-io/velaterm/vsearch.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 | $0.00141 | $0.01001 |
| Opus 5.5 | $0.00056 | $0.00400 |
| Sonnet 5.5 | $0.00028 | $0.00200 |
| Haiku 4.5 | $0.00014 | $0.00100 |
Grade A, and why
vsearch 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vsearch
vsearch searches conversation history across every vlx-term session on this machine, or within one
specified session. It is a pure read: nothing is written, and no other session is interrupted.
When to use it
Reach for it on your own initiative, without waiting to be asked:
- The user points at another conversation: "how did we fix this last time", "the approach from the other session", "that decision we made yesterday". The trigger is the meaning, in whatever language it comes.
- You hit an error, a config value, or an unfamiliar module that feels like it has come up before.
- You are about to make a design choice that an earlier session may already have settled.
The failure to avoid: telling the user that earlier conversations are out of reach. They are not. Search before you say something cannot be found.
Do not use it for searching code or files — that is what Grep and Glob are for. vsearch searches
conversations.
How to run it
vsearch <words...> [--session <session>] [--all|--archived] [--limit N] [--json]
- Multiple words are an implicit AND and word order does not matter. Two or three distinctive words work better than a long sentence.
--session <session>restricts the search to one session. It accepts the same full id, id prefix, exact name, or unique name substring asvrefer; quote names containing spaces. A specified session is searched whether live or archived unless an explicit scope flag is supplied;--archivedlimits it to archived targets, while--allretains the broad target scope.- By default only live sessions are searched. Add
--allto include archived ones, or--archivedto search only those. --limit Ncaps how many sessions come back (default 10).--jsongives the full machine-readable result, including every snippet.
What it searches
Conversations only. Sessions whose agent keeps a readable transcript — claude, codex, opencode, pi, omp, and grok — are the ones it can reach. Other agents store their history in private formats that are not parsed yet, so their sessions are invisible to it, as are plain terminal sessions. When a query matched such a session through its terminal recording, the output says how many were left out; that is expected, not a failure.
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 Changed · +4 lines · +5 tokens per session ecffc78d0ae9
- 1mo ago First seen · 79 lines · 136 tokens per session scan A d0227dd61add
vsearch is a skill published in the GitHub repository vlinx-io/VelaTerm (301 stars, last pushed 2d ago), licensed MIT. It adds 141 tokens to every session and 1,001 once invoked, about $0.0006 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 2026-09-08.
Other skills, from other repositories
forgetful-cli-setup
Set up the Forgetful CLI and connect from a terminal — install, local or remote mode, auth, and verification. Use when connecting a human or headless agent via shell, wiring CI with token auth, or operating a local server (serve, database selection, feature flags, re-embedding). Also covers the machine contract…
lpm-memory
Shared project memory for AI coding agents: save or recall work-session logs in /.lpm/memory/ / .md so another agent CLI (Claude Code, Codex, Gemini) or a future session can continue the work by session name. Invoke with a session id (e.g. /lpm-memory auth-refactor) to continue that session. Use when the user asks to…
corral
Query local Claude Code, Codex CLI, OpenCode, Kimi Code CLI, Cursor Agent CLI, and Pi session history through the corral CLI — list recent sessions, search by topic, read a session's conversation, export a shareable transcript with tool calls and thinking, or build a handoff context package to continue interrupted…
hermes-agent
Use when building self-learning AI agents that improve through experience — terminal-first interface, tool calling, memory persistence, autonomous task execution. Hermes Agent: self-improving general-purpose AI agent with local-first architecture.
meditate
End-of-session reflection generating persistent learnings about user preferences, communication patterns, and cross-session insights. Activates when wrapping up a session, or when user says "let's wrap up", "end the session", "time to reflect", or "meditate". Also extracts judgment rules from decisions made during the…
wiki
Maintain Claudia's wiki, a directory of synthesized Markdown pages about your active entities (people, projects, organizations, topics). Each page is written by Claudia from raw memories, cites its sources, flags contradictions, and grows over time. Use when user says "write a wiki page for [entity]", "what do you…