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/ruya-ai/cozempic/session-startgit clone --depth 1 https://github.com/Ruya-AI/cozempicWrote 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/ruya-ai/cozempic/session-start)<a href="https://agentmods.dev/hooks/ruya-ai/cozempic/session-start"><img src="https://agentmods.dev/badge/hooks/ruya-ai/cozempic/session-start.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
SessionStart 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.
How it starts
The opening of the file, as written. The whole thing — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"SessionStart": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "cozempic guard --daemon 2>/dev/null || true"
}
]
},
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "export COZEMPIC_NO_AUTO_INIT=1; HOOK_DATA=$(cat); SESSION_ID=$(echo \"$HOOK_DATA\" | PYTHONIOENCODING=utf-8 python3 -c \"import sys,json,re; s=json.load(sys.stdin).get('session_id','').lower(); print(re.sub(r'[^a-z0-9_-]','_',s))\" 2>/dev/null); TRANSCRIPT=$(echo \"$HOOK_DATA\" | PYTHONIOENCODING=utf-8 python3 -c \"import sys,json; print(json.load(sys.stdin).get('transcript_path',''))\" 2>/dev/null); SLUG=$(printf '%.12s' \"$SESSION_ID\"); { cozempic digest inject ${TRANSCRIPT:+--session \"$TRANSCRIPT\"} 2>/dev/null || python3 -m cozempic digest inject ${TRANSCRIPT:+--session \"$TRANSCRIPT\"} 2>/dev/null; } || true; [ -n \"$SESSION_ID\" ] && { STATUS_FILE=\"/tmp/cozempic_reload_${SLUG}.status\"; if [ -f \"$STATUS_FILE\" ]; then echo \"Cozempic: previous reload may have failed — $(head -n 3 $STATUS_FILE 2>/dev/null | tail -n 1)\"; rm -f \"$STATUS_FILE\"; fi; }; [ -n \"$SESSION_ID\" ] && (export COZEMPIC_NO_GLOBAL_INIT=1; if command -v flock >/dev/null 2>&1; then flock -n 9 || exit 0; fi; SENTINEL_FILE=\"/tmp/cozempic_reload_${SLUG}.in-flight\"; if [ -f \"$SENTINEL_FILE\" ] && [ $(( $(date +%s) - $(stat -f %m \"$SENTINEL_FILE\" 2>/dev/null || stat -c %Y \"$SENTINEL_FILE\" 2>/dev/null || echo 0) )) -lt 120 ]; then echo \"Cozempic: reload in flight, skipping guard spawn\"; exit 0; fi; if [ -z \"$COZEMPIC_NO_AUTO_UPDATE\" ] && [ -z \"$COZEMPIC_PIN\" ]; then PRE=$(cozempic --version 2>/dev/null | awk '/^cozempic /{print $2; exit}'); { uv pip install --upgrade cozempic --quiet 2>/dev/null || pip install --upgrade cozempic --quiet --disable-pip-version-check 2>/dev/null || python3 -m pip install --upgrade cozempic --quiet --disable-pip-version-check 2>/dev/null; } && POST=$(cozWhat else settings.json configures
This page is one entry in a file that holds 6. 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 · 22 lines scan A 1c7d880a3f02
SessionStart is a hook published in the GitHub repository Ruya-AI/cozempic (379 stars, last pushed 2mo 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
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing chat-memory.py, bm25-memory.py and memory-keyword-trigger.py with --rich (3 commands). From pluto2060/CTX.
Stop
Runs when the agent finishes a response, executing auto_save.py via python. From ErebusEnigma/context-memory.
PreCompact
Runs before the context is compacted, executing pre_compact_save.py via python. From ErebusEnigma/context-memory.
SessionStart
Runs when a session starts on startup and resume, executing session-start.sh via bash. From johnnyjoy/pluribus.
PostToolUseFailure
Runs when a tool call fails, executing post-tool-failure-hint.sh via bash. From johnnyjoy/pluribus.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing user-prompt-recall.sh via bash. From johnnyjoy/pluribus.