agentmods.dev

SessionStart

A session-start hook that runs two media-control commands when a coding session opens: one detects media and the other prepares it in the background.

In plain words
What is it for?
Use it to initialize media detection and warmup whenever a session begins. The excerpt does not explain what media devices or apps it supports.
Why use it?
It automatically prepares media controls at the start of a session, so they do not need to be started manually.

Hook

4 1mo ago A scan tokens not measured original MIT
View the source file Bangs00/claude-media-control
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 hooks/bangs00/claude-media-control/session-start
Clone the repo
git clone --depth 1 https://github.com/Bangs00/claude-media-control
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 A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

SessionStart 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 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.

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.

hooks/hooks.json · 19 lines

What it actually says

{
  "SessionStart": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "\"${CLAUDE_PLUGIN_ROOT}/scripts/media.sh\" detect",
          "timeout": 10
        },
        {
          "type": "command",
          "command": "\"${CLAUDE_PLUGIN_ROOT}/scripts/media.sh\" warmup",
          "async": true,
          "timeout": 120
        }
      ]
    }
  ]
}
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 · 19 lines scan A 280943815557

Subscribe to this mod's changes

SessionStart is a hook published in the GitHub repository Bangs00/claude-media-control (4 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. 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.

claude-codeclaude-code-marketplaceclaude-code-pluginclaude-pluginmacosmedia-control
Related

Other hooks, from other repositories

PreToolUse

Runs before the agent uses a tool for Edit, Write, MultiEdit and NotebookEdit tool calls, executing gate.py via python3. From emanzurv/quiz-me-skill.

emanzurv/quiz-me-skill · not measured

SessionStart

Runs when a session starts on startup, resume, clear and compact, executing gate.py via python3 with --clear. From emanzurv/quiz-me-skill.

emanzurv/quiz-me-skill · not measured

StopFailure

Runs on the StopFailure event for server_error, overloaded, rate_limit, authentication_failed, oauth_org_not_allowed, billing_error, invalid_request, model_not_found, max_output_tokens and unknown tool calls, executing activity.ts via bun. From 2naive/claude-telegram-topics.

2naive/claude-telegram-topics · not measured

Stop

Runs when the agent finishes a response, executing activity.ts and mirror.ts via bun (2 commands). From 2naive/claude-telegram-topics.

2naive/claude-telegram-topics · not measured

UserPromptSubmit

Runs when you submit a prompt, before the agent sees it, executing activity.ts via bun. From 2naive/claude-telegram-topics.

2naive/claude-telegram-topics · not measured

PreToolUse

Runs before the agent uses a tool, executing activity.ts via bun. From 2naive/claude-telegram-topics.

2naive/claude-telegram-topics · not measured