install-agent

A command for fetching a GitHub code repository into a temporary local folder so it can be examined. If the repository is already there, it pulls the latest changes.

In plain words
What is it for?
Use it when a user provides a GitHub link and wants the repository explored, reviewed, or explained.
Why use it?
It saves the manual steps of downloading a repository and locating its important files before analysis.

Skill for Claude CodeCodex

Part of the agent-factory plugin — 7 skills shipped together

Install

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.

agentmods
npx agentmods add skills/gettalon/talon-plugins/install-agent
Any agent
npx skills add gettalon/talon-plugins --skill install-agent
Clone the repo
git clone --depth 1 https://github.com/gettalon/talon-plugins

Made for: Claude Code, Codex.

Or install agent-factory, the plugin that ships this one along with the rest of its 7 skills.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 378 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.00378
Opus 5 $0.00026 $0.00189
Sonnet 5 $0.00010 $0.00076
Haiku 4.5 $0.00005 $0.00038

Measured 2d ago against content hash e5b4ed147d56, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

install-agent 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 2d 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.

plugins/agent-factory/skills/install-agent/SKILL.md · 46 lines

What it actually says

Install Agent — Fetch GitHub Repo for Analysis

When the user pastes a GitHub URL, pull the repo locally so you can read and analyze its contents.

$ARGUMENTS

Process

Step 1: Parse the URL

Accept these formats:

  • https://github.com/user/repo
  • https://github.com/user/repo.git
  • [email protected]:user/repo.git
  • user/repo (expand to https://github.com/user/repo)

Extract the repo name from the URL.

Step 2: Clone or Pull

Target directory: /tmp/repos/<repo-name>

  • If the directory doesn't exist: git clone <url> /tmp/repos/<repo-name>
  • If it already exists: cd /tmp/repos/<repo-name> && git pull

Step 3: Analyze

Once cloned, explore the repo:

  1. Show the directory structure (ls or find top-level)
  2. Read key files: README, config files, entry points
  3. Summarize what the repo is and what it does
  4. Answer whatever the user asked about it

Notes

  • This is a lightweight fetch — just clone to /tmp for reading, not a permanent install
  • If the clone fails (private repo, bad URL), tell the user and suggest fixes
  • If the user wants to install the repo as a Talon agent, use /create-agent or /compose-agent after analysis
Changes

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.

  1. 2d ago First seen · 46 lines · 51 tokens per session scan A e5b4ed147d56

Subscribe to this mod's changes

install-agent is a skill published in the GitHub repository gettalon/talon-plugins (6 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 378 once invoked, about $0.0003 per session on Opus 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.

Related

Other skills, from other repositories