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

Recon

by gavraz in gavraz/recon

Manage Claude Code tmux sessions via the recon CLI. An agent skill from gavraz/recon.

MITAuto-check passed

Install Recon

skills CLI
$ npx skills add gavraz/recon --skill recon -a claude-code

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

GitHub CLI
$ gh skill install gavraz/recon recon --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/gavraz/recon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/recon .claude/skills/recon && 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
recon
GitHub stars
264
Token cost
~167 tokens
SKILL.md length
86 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Manage Claude Code tmux sessions via the recon CLI. An agent skill from gavraz/recon.

  • Works in 2 steps: Discover capabilities → Execute the task
  • SKILL.md covers Step 1: Discover capabilities and Step 2: Execute the task
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Recon is an agent skill from gavraz/recon. Manage Claude Code tmux sessions via the recon CLI

Its SKILL.md is about 170 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with tmux. The repository describes itself as: tmux-native dashboard for managing Claude Code agents. The licence is MIT.

Example prompts

  • “/recon”

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Discover capabilities
  2. Execute the task

What it can do on your machine

Read from SKILL.md and the folder at commit 707418b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    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

Recon loads about 167 tokens when it runs. Until then it costs about 14 tokens; SKILL.md has 86 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~14
When it runs · the whole SKILL.md, loaded when a task matches
~167

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 gavraz/recon at commit 707418b, republished under its MIT licence (© gavraz). 86 words, ~167 tokens.

Download SKILL.mdSave it as .claude/skills/recon/SKILL.md (or your agent's skills folder).
name
recon
description
Manage Claude Code tmux sessions via the recon CLI

You have access to recon, a CLI tool for monitoring and managing Claude Code sessions running in tmux.

Step 1: Discover capabilities

bash
recon --help

Step 2: Execute the task

Use the commands discovered in Step 1. Common examples:

  • recon — open the table dashboard
  • recon view — open the visual dashboard
  • recon new — interactive form to create a new session
  • recon next — jump to the next agent waiting for input
  • recon resume — interactive picker to resume a past session
  • recon json — get all session state as JSON (useful for scripting)

© gavraz, 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 .claude/skills/recon of gavraz/recon.

Open the folder on GitHubat commit 707418b

Compare with similar skills

Recon 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.

Recon compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Recon this skillgavraz/recon264—~167Automated safety check: PassMIT
Codex Plugin QAcode-yeongyu/oh-my-openagent70k1 repos~1.9kAutomated safety check: PassCustom licence
Tmuxopenclaw/openclaw392k2 repos~640Automated safety check: PassMIT
1passwordtrpc-group/trpc-agent-go1.8k15 repos~656Automated safety check: PassApache-2.0
CodeGraph Agent Evalcolbymchenry/codegraph73k—~950Automated safety check: PassMIT
Tmuxtrpc-group/trpc-agent-go1.8k24 repos~868Automated safety check: PassApache-2.0

Similar skills

  • Codex Plugin QA

    code-yeongyu/oh-my-openagent

    Tests the omo Codex plugin in an isolated CODEX_HOME with a local mock model, proving hooks fired through app-server notifications without touching ~/.codex.

    70k GitHub starsUsed in 1 repo~1.9k tokens
    Testing & QAAuto-check passed

  • Tmux

    openclaw/openclaw

    Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.

    392k GitHub starsUsed in 2 repos~640 tokens
    Auto-check passed

  • 1password

    trpc-group/trpc-agent-go

    Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.

    1.8k GitHub starsUsed in 15 repos~656 tokens
    AI & LLM EngineeringAuto-check passed

  • CodeGraph Agent Eval

    colbymchenry/codegraph

    Benchmarks how much CodeGraph helps a coding agent on a real repository, comparing runs with and without it for a chosen local or published version.

    73k GitHub stars~950 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Tmux

    trpc-group/trpc-agent-go

    Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

    1.8k GitHub starsUsed in 24 repos~868 tokens
    Data & AnalyticsAuto-check passed

  • CodexBar Live QA

    steipete/CodexBar

    Runs live QA for the CodexBar app: provider usage matrix checks through its packaged CLI, config validation and menu checks, with 1Password-backed credentials handled safely.

    22k GitHub stars~1.2k tokensUpdated today
    Testing & QAAuto-check passed

Works with

Questions about Recon

What does Recon do?

Manage Claude Code tmux sessions via the recon CLI. An agent skill from gavraz/recon. Recon is an agent skill from gavraz/recon.

How do I install Recon in Claude Code?

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

How do I install Recon in Codex?

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

Can I use Recon 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 gavraz/recon --skill recon -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recon, .gemini/skills/recon, .github/skills/recon and .opencode/skills/recon in your project.

What does Recon need to run?

SKILL.md names no scripts, command-line tools or credentials: Recon is instructions for the agent only.

Does Recon 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 Recon 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 Recon use?

Recon 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 Recon use?

About 167 tokens (SKILL.md is roughly 668 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 Recon?

Skills that share tags, products or a category with Recon: Codex Plugin QA (code-yeongyu/oh-my-openagent, 70k stars), Tmux (openclaw/openclaw, 392k stars), 1password (trpc-group/trpc-agent-go, 1.8k stars) and CodeGraph Agent Eval (colbymchenry/codegraph, 73k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Recon?

gavraz (a GitHub user) maintains it in gavraz/recon, which has 264 GitHub stars. The repository was last updated on July 17, 2026.

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