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 hooks/jagoff/memo/user-prompt-submitgit clone --depth 1 https://github.com/jagoff/memoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/hooks/jagoff/memo/user-prompt-submit)<a href="https://agentmods.dev/hooks/jagoff/memo/user-prompt-submit"><img src="https://agentmods.dev/badge/hooks/jagoff/memo/user-prompt-submit.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
UserPromptSubmit 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 4d 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.
What it actually says
{
"UserPromptSubmit": [
{
"hooks": [
{
"type": "command",
"command": "MEMO_NONINTERACTIVE=1 memo session autosave",
"timeout": 5,
"comment": "Increased from 3s: DB writes can be slow on first call"
},
{
"type": "command",
"command": "MEMO_NONINTERACTIVE=1 MEMO_AGENT_TTY=${MEMO_AGENT_TTY:-$(tty 2>/dev/null | grep -E '^/dev/' | head -1)} memo session idle-maintenance --mode capture",
"timeout": 30,
"async": true,
"comment": "Idle capture: waits for a quiet window (MEMO_SESSION_IDLE_CAPTURE_SECS, default 10s) after the turn finishes and then mines the current session chunk into durable memorias. MEMO_AGENT_TTY captures the terminal PTY so the notification writes directly to the user's terminal. Stale workers self-cancel if a newer prompt updated the session snapshot. Async + soft-fail. Disable with MEMO_CAPTURE_DISABLE=1."
},
{
"type": "command",
"command": "MEMO_NONINTERACTIVE=1 memo session checkpoint",
"timeout": 5,
"async": true
},
{
"type": "command",
"command": "MEMO_NONINTERACTIVE=1 memo sync auto",
"timeout": 90,
"async": true,
"comment": "Durable in-session GitHub sync: self-throttled (MEMO_SYNC_PUSH_DEBOUNCE_S / MEMO_SYNC_PULL_INTERVAL_S) so a crashed/long session doesn't strand hours of memorias until Stop, and a long session converges on another Mac's pushes without a restart. Cheap no-op (timestamp check, no git) when not due; soft no-ops on non-git installs. Async so it never touches the recall 5s budget. Disable with MEMO_SYNC_AUTO=0."
}
]
}
]
}What else hooks.json configures
This page is one entry in a file that holds 4. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 4d ago First seen · 34 lines scan A 9f6a5469d286
UserPromptSubmit is a hook published in the GitHub repository jagoff/memo (16 stars, last pushed 4d 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 2026-08-30.
Other hooks, from other repositories
SessionStart
Runs when a session starts, running echo 'Session start -- read MEMORY.md and SCRATCHPAD.md to r. From fo0/clawstash.
PostToolUse
Runs after a tool call finishes, running python3 -m memory.hooks PostToolUse. From Verace-Pvt-Ltd/agentic-memory.
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing format_and_lint.sh. From supabase/supabase.
SessionStart
Runs when a session starts, executing on-start.js via node. From google-gemini/gemini-cli.
SessionStart
Runs when a session starts on startup, executing install_pkgs.sh. From supabase/supabase.
PreToolUse
Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From apache/superset.