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/nickmisasi/planner/settingsgit clone --depth 1 https://github.com/nickmisasi/plannerGrade A, and why
planner 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": "echo '=== PLANNING REPO SESSION START ===' && echo '' && echo 'Reading registry.yaml for current project state:' && echo '' && cat registry.yaml && echo '' && echo '---' && echo 'IMPORTANT: Read CLAUDE.md for full instructions. If the user wants to continue work, use the /continue skill. Available skills: /new-project, /new-idea, /continue, /iterate, /research, /spike, /export, /status'"
}
]
}
],
"Stop": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "echo 'REMINDER: If you were working on an idea, ensure session.md has been updated with current progress, decisions, open questions, and next steps before ending this session.'"
}
]
}
],
"PreCompact": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "echo '=== CONTEXT COMPACTION REMINDER ===' && echo '' && echo 'This is an AI-first planning repository. Key files:' && echo '- CLAUDE.md: Full agent instructions' && echo '- registry.yaml: Master project index' && echo '- .claude/skills/: Slash command definitions' && echo '' && echo 'Current registry state:' && cat registry.yaml && echo '' && echo 'Available skills: /new-project, /new-idea, /continue, /iterate, /research, /spike, /export, /status'"
}
]
}
]
}
}
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 · 38 lines scan A 1a46e35747e2
planner is a settings file published in the GitHub repository nickmisasi/planner (5 stars, last pushed 4mo 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
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
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).
ui-ux-pro-max-skill
Agent settings declaring 7 allowed tools.