New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Vsearch

by vlinx-io in vlinx-io/VelaTerm

You CAN search other sessions' conversations. An agent skill from vlinx-io/VelaTerm.

MITAuto-check passedBackend & APIs

Install Vsearch

skills CLI
$ npx skills add vlinx-io/VelaTerm --skill vsearch -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vlinx-io/VelaTerm vsearch --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vlinx-io/VelaTerm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/vsearch .claude/skills/vsearch && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vsearch
GitHub stars
275
Token cost
~1.1k tokens
SKILL.md length
556 words
Files
1
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

You CAN search other sessions' conversations. An agent skill from vlinx-io/VelaTerm.

  • The user gestures at earlier work — last time
  • SKILL.md covers When to use it, How to run it, What it searches and Reading the output, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • We solved this before

What it does

Vsearch is an agent skill from vlinx-io/VelaTerm. You CAN search other sessions' conversations. This is a full-text search across every vlx-term session on this machine or within one specified session, so a past discussion is findable even when nobody remembers which session held it. Use it whenever the user gestures at earlier work — "last time", "we solved this before", "the other branch", "didn't we discuss this" — in any language, and use it on your own initiative when an error or design question feels like one already settled somewhere. Search first, then…

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Search implementation. The repository describes itself as: VelaTerm = Codex + iTerm2, The Best ADE for AI Coding. The licence is MIT.

When your agent uses it

  • The user gestures at earlier work — last time
  • We solved this before
  • The other branch
  • Didnt we discuss this — in any language

Example prompts

  • “last time”
  • “we solved this before”
  • “the other branch”
  • “/vsearch”

Requirements

  • Pre-approved tools (allowed-tools): Bash(vsearch:*)

What it can do on your machine

Read from SKILL.md and the folder at commit 98b5f2f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(vsearch:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vsearch loads about 1.1k tokens when it runs. Until then it costs about 172 tokens; SKILL.md has 556 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~172
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vlinx-io/VelaTerm at commit 98b5f2f, republished under its MIT licence (© vlinx-io). 556 words, ~1,069 tokens.

Download SKILL.mdSave it as .claude/skills/vsearch/SKILL.md (or your agent's skills folder).
name
vsearch
description
You CAN search other sessions' conversations. This is a full-text search across every vlx-term session on this machine or within one specified session, so a past discussion is findable even when nobody remembers which session held it. Use it whenever the user gestures at earlier work — "last time", "we solved this before", "the other branch", "didn't we discuss this" — in any language, and use it on your own initiative when an error or design question feels like one already settled somewhere. Search first, then read the conversation with vrefer. Never claim past sessions are unreachable. Read-only: nothing is disturbed. Available only inside vlx-term-hosted local sessions.
allowed-tools
Bash(vsearch:*)

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

bash
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 as vrefer; quote names containing spaces. A specified session is searched whether live or archived unless an explicit scope flag is supplied; --archived limits it to archived targets, while --all retains the broad target scope.
  • By default only live sessions are searched. Add --all to include archived ones, or --archived to search only those.
  • --limit N caps how many sessions come back (default 10).
  • --json gives 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.

Show full SKILL.md (198 more words)Show less

Reading the output

Each hit shows the session name, the first eight characters of its id, how many matches it has, and up to three snippets. The msg N in front of a snippet is that message's index, which vrefer --range takes directly. Text output caps the snippets on purpose; use --json when you need them all.

Every hit ends with the command that reads that conversation in full:

    full transcript: vrefer a9af7b1c

That is the intended next step — search for the overview, then vrefer the session that looks right.

Notes

  • no matches on stdout with exit code 0 is a normal answer, not a failure. Say so plainly and move on.
  • The first search after a lot of new conversation activity refreshes the index and can take a few seconds. It is working, not stuck — do not retry it.
  • What you find comes from other sessions, not this one's history. When you use it, say where it came from.
  • Must run inside a vlx-term-hosted local session: it relies on the injected VLX_* environment variables and vsearch on PATH. If it reports "not inside a VelaTerm session", the command is simply unavailable here — say so instead of looking for another way in.

© vlinx-io, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/vsearch of vlinx-io/VelaTerm.

Open the folder on GitHubat commit 98b5f2f

Compare with similar skills

Vsearch next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vsearch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vsearch this skillvlinx-io/VelaTerm275—~1.1kAutomated safety check: PassMIT
Firecrawl Search Integrationfirecrawl/firecrawl190k1 repos~1.1kAutomated safety check: PassISC
Product Full-Text Searchlobehub/lobehub83k—~4.1kAutomated safety check: PassCustom licence
Hackernewssigcli/sigcli293—~2kAutomated safety check: PassMIT
Create Skillxlanex6/nuxt-meilisearch123—~752Automated safety check: PassMIT
Foundatio Repositoriesexceptionless/Exceptionless2.5k—~1.9kAutomated safety check: PassApache-2.0

Similar skills

  • Firecrawl Search Integration

    firecrawl/firecrawl

    Guidance for adding Firecrawl's /search endpoint to product code and agent workflows when a feature starts from a query rather than a URL.

    190k GitHub starsUsed in 1 repo~1.1k tokens
    Backend & APIsAuto-check passed

  • Product Full-Text Search

    lobehub/lobehub

    Guides work on LobeHub's own product search: the shared search repository, provider choice, Elasticsearch mappings, change syncing and reindexing.

    83k GitHub stars~4.1k tokensUpdated today
    Backend & APIsAuto-check passed

  • Hackernews

    sigcli/sigcli

    Interact with Hacker News (news.ycombinator.com) — browse top, new, and best stories, read item details and comment threads, look up user profiles, and search posts via Algolia.

    293 GitHub stars~2k tokensUpdated 11 days ago
    Backend & APIsAuto-check passed

  • Create Skill

    xlanex6/nuxt-meilisearch

    Guide for creating effective skills following best practices.

    123 GitHub stars~752 tokensUpdated 3 mo ago
    Backend & APIsAuto-check passed

  • Foundatio Repositories

    exceptionless/Exceptionless

    Query, aggregate, patch, or paginate Exceptionless data through its Elasticsearch repository abstractions.

    2.5k GitHub stars~1.9k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Meilisearch

    xlanex6/nuxt-meilisearch

    Meilisearch open-source search engine with full-text, semantic, and hybrid search, filtering, faceting, and typo tolerance.

    123 GitHub stars~1.1k tokensUpdated 3 mo ago
    Backend & APIsAuto-check passed

More from vlinx-io/VelaTerm

All 26 skills in this repo

  • Assess Patch Risk

    vlinx-io/VelaTerm

    Assess an immutable patch artifact's program impact, regression risk, and auto-merge eligibility.

    275 GitHub stars~2.1k tokensUpdated 2 days ago
    Auto-check passed

  • Vspawn

    vlinx-io/VelaTerm

    Explicitly spawn a standalone child session under the current vlx-term session, passing the task in as its first message (mirrors spawntask).

    275 GitHub stars~2.5k tokensUpdated 2 days ago
    Auto-check passed

  • Deep Security Scan

    vlinx-io/VelaTerm

    A skill your agent uses when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide or scoped-path Codex Security scan.

    275 GitHub stars~3.3k tokensUpdated 2 days ago
    Auto-check passed

  • Define Security Policy

    vlinx-io/VelaTerm

    Define, review, or update SECURITY.md guidance for a repository or component.

    275 GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed

  • Track Findings

    vlinx-io/VelaTerm

    Track validated Codex Security findings in Linear, Jira, GitHub issues, or draft GitHub security advisories.

    275 GitHub stars~5.1k tokensUpdated 2 days ago
    Auto-check passed

  • Verify Fix

    vlinx-io/VelaTerm

    Use only when the user explicitly requests verification that a security fix remediates a reported vulnerability.

    275 GitHub stars~757 tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Vsearch

What does Vsearch do?

You CAN search other sessions' conversations. An agent skill from vlinx-io/VelaTerm. Vsearch is an agent skill from vlinx-io/VelaTerm. You CAN search other sessions' conversations.

When should I use Vsearch?

Vsearch fits situations like: the user gestures at earlier work — last time; we solved this before; the other branch; didnt we discuss this — in any language.

How do I install Vsearch in Claude Code?

Run `npx skills add vlinx-io/VelaTerm --skill vsearch -a claude-code`. Or copy the skill folder (skills/vsearch in vlinx-io/VelaTerm) into .claude/skills/vsearch in your project. Claude Code loads it when a task matches its description.

How do I install Vsearch in Codex?

Run `npx skills add vlinx-io/VelaTerm --skill vsearch -a codex`. Or copy the skill folder (skills/vsearch in vlinx-io/VelaTerm) into .agents/skills/vsearch in your project. Codex loads it when a task matches its description.

Can I use Vsearch in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vlinx-io/VelaTerm --skill vsearch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vsearch, .gemini/skills/vsearch, .github/skills/vsearch and .opencode/skills/vsearch in your project.

What does Vsearch need to run?

SKILL.md names no scripts, command-line tools or credentials: Vsearch is instructions for the agent only. Its frontmatter pre-approves these tools: Bash(vsearch:*).

Does Vsearch access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vsearch safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vsearch use?

Vsearch is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vsearch use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vsearch?

Skills that share tags, products or a category with Vsearch: Firecrawl Search Integration (firecrawl/firecrawl, 190k stars), Product Full-Text Search (lobehub/lobehub, 83k stars), Hackernews (sigcli/sigcli, 293 stars) and Create Skill (xlanex6/nuxt-meilisearch, 123 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vsearch?

vlinx-io (a GitHub user) maintains it in vlinx-io/VelaTerm, which has 275 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 7, 2026.

Source: vlinx-io/VelaTerm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.