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/sefaertunc/worclaude/session-startgit clone --depth 1 https://github.com/sefaertunc/WorclaudeGrade 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": "",
"hooks": [
{
"type": "command",
"command": "echo '=== CLAUDE.md ==='; cat CLAUDE.md 2>/dev/null; echo; echo '=== PROGRESS ==='; cat docs/spec/PROGRESS.md 2>/dev/null; echo; echo '=== LAST SESSION ==='; f=$(ls -t .claude/sessions/*.md 2>/dev/null | head -1); if [ -n \"$f\" ]; then cat \"$f\"; else echo 'No previous session found'; fi; echo; echo '=== BRANCH ==='; git rev-parse --abbrev-ref HEAD 2>/dev/null || echo 'not a git repo'; echo; echo '=== RECENT LEARNINGS ==='; if [ -f .claude/learnings/index.json ]; then node -e \"const idx=JSON.parse(require('fs').readFileSync('.claude/learnings/index.json','utf8'));idx.learnings.sort((a,b)=>b.created.localeCompare(a.created)).slice(0,5).forEach(l=>console.log('- ['+l.category+'] '+l.file));\" 2>/dev/null; else echo 'No learnings captured yet. Use [LEARN] blocks to capture corrections.'; fi"
}
]
}
]
}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 · 13 lines scan A c32a0f2d7e12
SessionStart is a hook published in the GitHub repository sefaertunc/Worclaude (4 stars, last pushed 23d 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
SubagentStop
Runs when a subagent finishes, executing subagent-stop-handler.js via node. From Joncik91/ucai.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing pipeline-prompt.sh. From Pierry/harness-kit.
PreCompact
Runs before the context is compacted, executing pre-compact.sh via bash. From awrshift/claude-memory-kit.
SessionStart
Runs when a session starts, executing index-sessions.sh via bash with --recent. From bashiraziz/llm-wiki-template.
Stop
Runs when the agent finishes a response, executing dejavu-hook.py via python. From HthSolid/claude-dejavu.
PostToolUse
Runs after a tool call finishes for Task and TodoWrite tool calls, running entire hooks claude-code post-task (2 commands). From liatrio-labs/ai-prompts.