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/rasputinkaiser/self-improvement-plugin/session-startgit clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-PluginGrade 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 2d 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
{
"SessionStart": [
{
"matcher": "startup|resume|clear|compact",
"hooks": [
{
"type": "command",
"command": "python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}\"/scripts/hook_event_tap.py --event SessionStart --script validate_harness.py -- python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}\"/scripts/validate_harness.py",
"timeout": 12,
"statusMessage": "Harness drift check"
},
{
"type": "command",
"command": "python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}\"/scripts/hook_event_tap.py --event SessionStart --script memory_fabric_doctor.py -- python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}\"/scripts/memory_fabric_doctor.py",
"timeout": 10,
"statusMessage": "Memory Fabric doctor + recent"
},
{
"type": "command",
"command": "python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}\"/scripts/hook_event_tap.py --event SessionStart --script proactive_drift.py -- python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}\"/scripts/proactive_drift.py",
"timeout": 7,
"statusMessage": "Proactive drift"
},
{
"type": "command",
"command": "python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}\"/scripts/hook_event_tap.py --event SessionStart --script agent_patterns.py -- python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}\"/scripts/agent_patterns.py --brief",
"timeout": 10,
"statusMessage": "Agent patterns brief"
},
{
"type": "command",
"command": "python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}\"/scripts/hook_event_tap.py --event SessionStart --script improvement_injector.py -- python3 \"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}\"/scripts/improvement_injector.py",
"timeout": 8,
"statusMessage": "Improvement injector (loop closure)"
}
]
}
]
}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.
- 2d ago First seen · 39 lines scan A c1ea5e7844be
SessionStart is a hook published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (6 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 2026-08-31.
Other hooks, from other repositories
PreToolUse
Runs before the agent uses a tool for Bash tool calls, executing test-filter.ts via bun. From first-fluke/oh-my-agent.
PreToolUse
Runs before the agent uses a tool for Edit, Write and Bash tool calls, executing cc10x_pretooluse_guard.py and cc10x_git_guard.py via python3 (2 commands). From romiluz13/cc10x.
PostCompact
Runs after the context is compacted, executing cc10x_event_logger.py via python3. From romiluz13/cc10x.
SubagentStop
Runs when a subagent finishes, executing cc10x_event_logger.py via python3. From romiluz13/cc10x.
StopFailure
Runs on the StopFailure event, executing cc10x_event_logger.py via python3. From romiluz13/cc10x.
PermissionDenied
Runs on the PermissionDenied event, executing dev-hook.mjs with --hook. From FailproofAI/failproofai.