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/reflexioai/claude-smart/session-endgit clone --depth 1 https://github.com/ReflexioAI/claude-smartGrade A, and why
SessionEnd 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.
This is a copy
86% identical to SessionStart — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"SessionEnd": [
{
"hooks": [
{
"type": "command",
"command": "_R=\"${CLAUDE_PLUGIN_ROOT}\"; [ -z \"$_R\" ] && _R=\"$HOME/.claude/plugins/marketplaces/reflexioai/plugin\"; bash \"$_R/scripts/hook_entry.sh\" claude-code session-end",
"timeout": 300
},
{
"type": "command",
"command": "_R=\"${CLAUDE_PLUGIN_ROOT}\"; [ -z \"$_R\" ] && _R=\"$HOME/.claude/plugins/marketplaces/reflexioai/plugin\"; bash \"$_R/scripts/dashboard-service.sh\" session-end",
"timeout": 10
},
{
"type": "command",
"command": "_R=\"${CLAUDE_PLUGIN_ROOT}\"; [ -z \"$_R\" ] && _R=\"$HOME/.claude/plugins/marketplaces/reflexioai/plugin\"; bash \"$_R/scripts/backend-service.sh\" session-end",
"timeout": 10
}
]
}
]
}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 · 23 lines scan A 6c7c1e683fe2
SessionEnd is a hook published in the GitHub repository ReflexioAI/claude-smart (774 stars, last pushed 3d ago), licensed Apache-2.0. 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. It is 86% identical to SessionStart, differing in 18 lines, and is treated as a copy.
Other hooks, from other repositories
PostToolUse
Runs after a tool call finishes for Write, Edit, MultiEdit, apply_patch and Agent tool calls, executing warden-shim.sh via bash (7 commands). From sliamh11/Deus.
SessionStart
Runs when a session starts, executing warden-shim.sh, linear_pending_hook.py and session_preflight_hook.py via bash (3 commands). From sliamh11/Deus.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing memory_retrieval_hook.py and warden-shim.sh via bash (2 commands). From sliamh11/Deus.
Stop
Runs when the agent finishes a response, executing nonumb-gate.sh via bash. From sliamh11/Deus.
SessionStart
Runs when a session starts on startup and resume, executing cloud-setup.sh via bash. From subkoks/BEST-Self-Enhancement-Learning-AI.
PreToolUse
Runs before the agent uses a tool for Write, Edit, MultiEdit, apply_patch, ExitPlanMode, ExitPlanMode, Task, Agent, Write, apply_patch and Bash tool calls, executing warden-shim.sh, tdd-test-lock.sh and format-check.sh via bash (10 commands). From sliamh11/Deus.