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.
npx agentmods add settings/noisy/noisy-coding/settingsgit clone --depth 1 https://github.com/noisy/noisy-codingGrade A, and why
noisy-coding 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 yesterday.
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.
What it actually says
{
"hooks": {
"UserPromptSubmit": [
{
"hooks": [
{
"type": "command",
"command": "NOISY_CODING_LISTENER_PORT=7765 python3 \"$CLAUDE_PROJECT_DIR/hooks/user_prompt_submit.py\"",
"timeout": 5,
"statusMessage": "Reporting activity (dev)"
}
]
}
],
"PreToolUse": [
{
"matcher": "mcp__noisy-coding-dev__speak",
"hooks": [
{
"type": "command",
"command": "NOISY_CODING_LISTENER_PORT=7765 python3 \"$CLAUDE_PROJECT_DIR/hooks/pre_speak.py\"",
"timeout": 5,
"statusMessage": "Showing spoken text (dev)"
}
]
},
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "NOISY_CODING_LISTENER_PORT=7765 python3 \"$CLAUDE_PROJECT_DIR/hooks/pre_tool_use.py\"",
"timeout": 5,
"statusMessage": "Reporting activity (dev)"
}
]
}
],
"PostToolUse": [
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "NOISY_CODING_LISTENER_PORT=7765 python3 \"$CLAUDE_PROJECT_DIR/hooks/post_tool_use.py\"",
"timeout": 5,
"statusMessage": "Checking voice queue (dev)"
}
]
}
],
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "NOISY_CODING_LISTENER_PORT=7765 python3 \"$CLAUDE_PROJECT_DIR/hooks/stop.py\"",
"timeout": 3630,
"asyncRewake": true,
"statusMessage": "Listening for your voice (dev)",
"rewakeSummary": "🎙️ Voice message received (dev)"
}
]
}
]
}
}
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.
- yesterday First seen · 68 lines scan A 7ae8e8e7fe68
noisy-coding is a settings file published in the GitHub repository noisy/noisy-coding (6 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other settings, from other repositories
pipecat
Agent settings configuring attribution.
kesha-voice-kit
Agent settings declaring 2 hook events (PostToolUse, PreToolUse) and 37 allowed tools.
superturtle
Agent settings configuring spinnerVerbs.
vox
Agent settings configuring hooks.
settings
MCP server for Audio Generation and Analysis with a Variety of Open Models.
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).