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/nvk/llm-wiki/session-startgit clone --depth 1 https://github.com/nvk/llm-wikiGrade 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.
Copies of this mod
5 near-identical copies found in the catalogue:
- PostToolUse — 94% identical, 5 lines differ
- UserPromptSubmit — 92% identical, 4 lines differ
- PreCompact — 89% identical, 5 lines differ
- Stop — 89% identical, 4 lines differ
- PostCompact — 84% identical, 5 lines differ
What it actually says
{
"SessionStart": [
{
"hooks": [
{
"type": "command",
"command": "python3 -c 'import glob,os,runpy,sys; p=os.path.join(os.environ.get(\"PLUGIN_ROOT\",\"\"),\"hooks\",\"llm_wiki_session.py\"); xs=glob.glob(os.path.expanduser(\"~/.codex/plugins/cache/llm-wiki/wiki/*/hooks/llm_wiki_session.py\")); p=p if os.path.isfile(p) else (max(xs,key=os.path.getmtime) if xs else \"\"); sys.exit(0) if not p else None; sys.argv=[p,*sys.argv[1:]]; runpy.run_path(p,run_name=\"__main__\")' hook --harness codex --if-enabled",
"timeout": 5,
"statusMessage": "Loading llm-wiki session context"
}
]
}
]
}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 · 14 lines scan A ca5a7b33dc16
SessionStart is a hook published in the GitHub repository nvk/llm-wiki (1,175 stars, last pushed 5d 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
FileChanged
Runs on the FileChanged event for .envrc, .env and .env.local tool calls, executing hooks.py via python3. From shanraisshan/claude-code-best-practice.
SessionEnd
Runs when a session ends, executing hooks.py via python3. From shanraisshan/claude-code-best-practice.
PermissionRequest
Runs when the agent asks permission for an action, executing hooks.py via python3. From shanraisshan/claude-code-best-practice.
InstructionsLoaded
Runs after instructions files are loaded for session_start, nested_traversal, path_glob_match, include and compact tool calls, executing validate-claude-md.py via python3. From alirezarezvani/ClaudeForge.
PostToolUse
Runs after a tool call finishes for Bash tool calls, executing capture-tool-result.sh via bash. From share-skills/pi.
PreToolUse
Runs before the agent uses a tool for Write, Edit, Bash, Agent, Task, SendMessage and TaskStop tool calls, running bash (3 commands). From modu-ai/moai-adk.