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/codename-11/subframe/settingsgit clone --depth 1 https://github.com/Codename-11/SubFrameGrade A, and why
SubFrame 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": {
"SessionStart": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "node -e \"try{require('./.subframe/hooks/session-start.js')}catch(e){if(e.code!=='MODULE_NOT_FOUND')throw e}\""
}
]
}
],
"UserPromptSubmit": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "node -e \"try{require('./.subframe/hooks/prompt-submit.js')}catch(e){if(e.code!=='MODULE_NOT_FOUND')throw e}\""
}
]
}
],
"Stop": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "node -e \"try{require('./.subframe/hooks/stop.js')}catch(e){if(e.code!=='MODULE_NOT_FOUND')throw e}\""
}
]
}
],
"PreToolUse": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "node -e \"try{require('./.subframe/hooks/pre-tool-use.js')}catch(e){if(e.code!=='MODULE_NOT_FOUND')throw e}\""
}
]
}
],
"PostToolUse": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "node -e \"try{require('./.subframe/hooks/post-tool-use.js')}catch(e){if(e.code!=='MODULE_NOT_FOUND')throw e}\""
}
]
}
]
}
}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 · 59 lines scan A d04927679e31
SubFrame is a settings file published in the GitHub repository Codename-11/SubFrame (10 stars, last pushed 8d 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
intuitive-flow
An empty agent settings file, from a project described as: Shared config, skills, and update scripts for Claude Code, Codex, and Gemini CLI.
ai-coding-agent-skills
Agent skills for AI coders.
known
Agent settings declaring 8 allowed tools.
dev-flow
An empty agent settings file, from a project described as: Engineering discipline for AI coding agents — from requirements through delivery.
vex
Agent settings declaring 2 hook events (PostToolUse, SessionEnd) and 32 allowed tools.
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).