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/hawkanng/claude-warden/session-startgit clone --depth 1 https://github.com/HawkannG/Claude-WardenWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/hooks/hawkanng/claude-warden/session-start)<a href="https://agentmods.dev/hooks/hawkanng/claude-warden/session-start"><img src="https://agentmods.dev/badge/hooks/hawkanng/claude-warden/session-start.svg" alt="Measured on agentmods" height="20"></a>Grade B, and why
SessionStart scanned grade B with 2 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
"command": "P=\"${CLAUDE_PROJECT_DIR:-.}\"; F=0; ls \"$P\"/.claude/hooks/warden-*.sh >/dev/null 2>&1 && F=1; grep -q '\\.claude/hooks/warden-' \"$P/.claude/settings.json\" 2>/dev/null && F=1; [ \"$F\" = 1 ] && echo '⚠️ O Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"command": "P=\"${CLAUDE_PROJECT_DIR:-.}\"; F=0; ls \"$P\"/.claude/hooks/warden-*.sh >/dev/null 2>&1 && F=1; grep -q '\\.claude/hooks/warden-' \"$P/.claude/settings.json\" 2>/dev/null && F=1; [ \"$F\" = 1 ] && echo '⚠️ O What it actually says
{
"SessionStart": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "rm -f \"${CLAUDE_PROJECT_DIR:-.}/.claude/warden-edit-tracker\"",
"timeout": 5
},
{
"type": "command",
"command": "P=\"${CLAUDE_PROJECT_DIR:-.}\"; F=0; ls \"$P\"/.claude/hooks/warden-*.sh >/dev/null 2>&1 && F=1; grep -q '\\.claude/hooks/warden-' \"$P/.claude/settings.json\" 2>/dev/null && F=1; [ \"$F\" = 1 ] && echo '⚠️ OLD WARDEN INSTALL DETECTED: Ghost hooks or files from a previous curl-based install found. Run /warden-setup to migrate (use --dry-run to preview).' >&2; exit 0",
"timeout": 5
}
]
}
]
}What else hooks.json configures
This page is one entry in a file that holds 4. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 4d ago First seen · 19 lines scan B a4017bc8282a
SessionStart is a hook published in the GitHub repository HawkannG/Claude-Warden (2 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). 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, running an inline shell check. From xiaolai/claudepot-app.
Setup
Runs once when the project is set up, executing hooks.py via python3. From shanraisshan/claude-code-best-practice.
PreToolUse
Runs before the agent uses a tool for Edit, Write, Grep, Glob, Bash, Edit, Write, NotebookEdit and Bash tool calls, executing spec-hint.js, module-hint.js and docs-hint.js via node (3 commands). From kaanozhan/Frame.
PostToolUse
Runs after a tool call finishes, running vibird hook PostToolUse. From Hakureirm/vibird.
PreToolUse
Runs before the agent uses a tool for Bash, shell_command, exec_command, unified_exec, apply_patch, Write and Edit tool calls, executing pre-tool-adapter.py via python3 (2 commands). From arbiterForge/codeArbiter.
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing format_and_lint.sh. From supabase/supabase.