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/kenimo49/compact-ops/session-startgit clone --depth 1 https://github.com/kenimo49/compact-opsGrade 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 yesterday.
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
{
"SessionStart": [
{
"matcher": "compact|resume",
"hooks": [
{
"type": "command",
"command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/sessionstart-recovery.sh\"",
"timeout": 5
}
]
}
]
}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 · 14 lines scan A 7e1e5b7074d7
SessionStart is a hook published in the GitHub repository kenimo49/compact-ops (3 stars, last pushed 27d 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 2026-08-31.
Other hooks, from other repositories
PostToolUse
Runs after a tool call finishes for Bash, Read, Grep, Glob, Write, Edit, MultiEdit, Agent, WebFetch, WebSearch, Bash, Read, Grep, Glob, Write, Edit, MultiEdit and Agent tool calls, executing posttool_guard.py, tool_profiler.py, task_result_collector.py and posttool_observers.js via python3 (4 commands). From…
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing prompt_budget_guard.py, parallel_hint.py, writer.py and retriever_wrapper.sh via python3 (4 commands). From soolaugust/vMem.
Stop
Runs when the agent finishes a response, executing extractor.py, output_governor.py, derive_rules.py and stop_coalesced.js via python3 (4 commands). From soolaugust/vMem.
SessionStart
Runs when a session starts, executing context_budget_guard.py and loader.py via python3 (2 commands). From soolaugust/vMem.
PreToolUse
Runs before the agent uses a tool for Read, Bash, Write, Edit and MultiEdit tool calls, executing filesize_guard.js and pretool_coalesced.js via node (2 commands). From soolaugust/vMem.
PreCompact
Runs before the context is compacted, executing pre_compact.py via python3. From soolaugust/vMem.