agentmods.dev

SessionStart

SessionStart is a hook for Claude Code from litestar-org/litestar-skills. Its token cost is not measured, scanned B, original, MIT.

A startup hook that runs a shell script when a coding session starts, is cleared, or is compacted. It adds project-specific Litestar reminders to the session context.

In plain words
What is it for?
Use it to run session-start setup and inject Litestar skill reminders at the beginning of relevant sessions.
Why use it?
It restores useful project guidance automatically instead of relying on the agent to remember it after a new or shortened session.

Hook for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the litestar plugin — 31 skills, 1 agent, 1 hook shipped together

not rated 14 17d ago B scan tokens not measured original MIT
View the source file litestar-org/litestar-skills
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add litestar-org/litestar-skills
Claude Code
/plugin install litestar

Made for: Claude Code.

Or install litestar, the plugin that ships this one along with the rest of its 31 skills, 1 agent, 1 hook.

Wrote 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.

agentmods badge for SessionStart

README.md
[![agentmods](https://agentmods.dev/badge/hooks/litestar-org/litestar-skills/session-start.svg)](https://agentmods.dev/hooks/litestar-org/litestar-skills/session-start)
Your own site
<a href="https://agentmods.dev/hooks/litestar-org/litestar-skills/session-start"><img src="https://agentmods.dev/badge/hooks/litestar-org/litestar-skills/session-start.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade B, and why

SessionStart scanned grade B with 1 finding 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 6d ago.

A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

"command": "r=\"${CLAUDE_PLUGIN_ROOT:-${PLUGIN_ROOT:-}}\"; if [ -n \"$r\" ] && [ ! -f \"${r%/}/hooks/session-start.sh\" ]; then r=\"\"; fi; if [ -z \"$r\" ] && [ -d \"$HOME/.claude/plugins/marketplaces\" ]; then r=\"$(fi
hooks/hooks.json · 16 lines

What it actually says

{
  "SessionStart": [
    {
      "matcher": "startup|clear|compact",
      "hooks": [
        {
          "name": "litestar-session-start",
          "type": "command",
          "command": "r=\"${CLAUDE_PLUGIN_ROOT:-${PLUGIN_ROOT:-}}\"; if [ -n \"$r\" ] && [ ! -f \"${r%/}/hooks/session-start.sh\" ]; then r=\"\"; fi; if [ -z \"$r\" ] && [ -d \"$HOME/.claude/plugins/marketplaces\" ]; then r=\"$(find -L \"$HOME/.claude/plugins/marketplaces\" -path \"*/litestar/hooks/session-start.sh\" -type f -print 2>/dev/null | sed 's#/hooks/session-start.sh$##' | head -n 1)\"; fi; if [ -z \"$r\" ] && [ -f ./hooks/session-start.sh ]; then r=\".\"; fi; [ -n \"$r\" ] || exit 0; CLAUDE_PLUGIN_ROOT=\"${r%/}\" bash \"${r%/}/hooks/session-start.sh\"",
          "description": "Inject project-aware Litestar skill reminders into the session context.",
          "async": false
        }
      ]
    }
  ]
}
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. 6d ago First seen · 16 lines scan B 0475c9ec5d05

Subscribe to this mod's changes

SessionStart is a hook published in the GitHub repository litestar-org/litestar-skills (14 stars, last pushed 17d ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

advanced-alchemyagent-skillsagentskillsai-agentsclaude-code-pluginclaude-code-skills
Related

Other hooks, from other repositories

SessionEnd

Runs when a session ends, executing capture-session-tail.sh. From Paretofilm/superpowers-gstack.

Paretofilm/superpowers-gstack · not measured

Stop

Runs when the agent finishes a response, executing session-stop.sh via bash. From IdoCohen560/claude-unity-game-studio.

IdoCohen560/claude-unity-game-studio · not measured

PostToolUse

Runs after a tool call finishes, executing run_hook.py via python3 (2 commands). From sbhooley/ainl-cortex.

sbhooley/ainl-cortex · not measured

TaskCompleted

Runs when a task is marked completed, executing task-completed.sh. From ben-alkov/the_swarm.

ben-alkov/the_swarm · not measured

SessionStart

Runs when a session starts, executing run_hook.py via python3. From sbhooley/ainl-cortex.

sbhooley/ainl-cortex · not measured

PostToolUse

Runs after a tool call finishes for Edit and Write tool calls, executing run-hook.cmd. From omas-odoo/odoo-superpowers.

omas-odoo/odoo-superpowers · not measured