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/jsohi/app-trading-engine/settingsgit clone --depth 1 https://github.com/jsohi/app-trading-engineGrade A, and why
app-trading-engine 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"effortLevel": "high",
"permissions": {
"ask": ["Bash(gh pr merge:*)"]
},
"hooks": {
"PreToolUse": [
{
"matcher": "ExitPlanMode",
"hooks": [
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/enforce-plan-design-before-exit.sh",
"timeout": 5,
"statusMessage": "Checking plan design gate (Plan-agent marker)..."
},
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/enforce-plan-review-before-exit.sh",
"timeout": 5,
"statusMessage": "Checking plan review gate (marker file)..."
}
]
},
{
"matcher": "TaskUpdate",
"hooks": [
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/enforce-review-before-complete.sh",
"timeout": 5,
"statusMessage": "Checking review + test gates before task completion..."
}
]
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/pre-tool-use.sh",
"timeout": 5,
"statusMessage": "Checking Linear issue convention..."
},
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/enforce-review-before-push.sh",
"timeout": 5,
"statusMessage": "Checking review + E2E gate..."
},
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/enforce-review-after-gemini.sh",
"timeout": 5,
"statusMessage": "Checking post-Gemini /review gate..."
},
{
"type": "prompt",
"prompt": "Check if this Bash command is: (1) a git push to main — if it pushes directly to main (e.g. 'git push origin main', or 'git push' whileWhat 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.
- 2d ago First seen · 128 lines scan A 4c38dd10b0cf
app-trading-engine is a settings file published in the GitHub repository jsohi/app-trading-engine (2 stars, last pushed 3mo ago), licensed Apache-2.0. 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
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
superset
Agent settings declaring 1 hook event (PreToolUse).
claude-cookbooks
Agent settings declaring 2 hook events (SessionStart, PreToolUse).
claude-code-best-practice
Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.
electron
Agent settings declaring 17 allowed tools.
uv
Agent settings declaring 2 hook events (SessionStart, PostToolUse).