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/baokhang83/fluencyloop/session-startgit clone --depth 1 https://github.com/baokhang83/fluencyloopGrade 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 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.
What it actually says
{
"SessionStart": [
{
"matcher": "startup",
"hooks": [
{
"type": "command",
"command": "plugin_root=\"${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}\"; if [ -n \"$plugin_root\" ]; then hook=\"$plugin_root/hooks/refresh-marketplace.sh\"; if [ ! -f \"$hook\" ] && [ -n \"${PLUGIN_ROOT:-}\" ]; then case \"$plugin_root\" in */plugins/cache/*/*/*) for candidate in \"${plugin_root%/*}\"/*/hooks/refresh-marketplace.sh; do if [ -f \"$candidate\" ]; then hook=\"$candidate\"; plugin_root=\"${candidate%/hooks/refresh-marketplace.sh}\"; fi; done ;; esac; fi; if [ -f \"$hook\" ]; then if [ -n \"${PLUGIN_ROOT:-}\" ]; then PLUGIN_ROOT=\"$plugin_root\" bash \"$hook\"; else CLAUDE_PLUGIN_ROOT=\"$plugin_root\" bash \"$hook\"; fi; fi; fi",
"commandWindows": "powershell.exe -NoProfile -ExecutionPolicy Bypass -Command \"$pluginRoot = $env:PLUGIN_ROOT; if ([string]::IsNullOrWhiteSpace($pluginRoot)) { $pluginRoot = $env:CLAUDE_PLUGIN_ROOT }; if (-not [string]::IsNullOrWhiteSpace($pluginRoot)) { $hook = Join-Path $pluginRoot 'hooks\\refresh-marketplace.ps1'; if (Test-Path -LiteralPath $hook -PathType Leaf) { & $hook } }\"",
"timeout": 30,
"statusMessage": "Checking FluencyLoop updates"
}
]
}
]
}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 · 16 lines scan A db1971b64641
SessionStart is a hook published in the GitHub repository baokhang83/fluencyloop (44 stars, last pushed 16d 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other hooks, from other repositories
SubagentStop
Runs when a subagent finishes, executing subagent-stop-validator.sh. From dralgorhythm/claude-agentic-framework.
TeammateIdle
Runs on the TeammateIdle event, executing notifier.cjs. From juspay/shooter.
PostToolUse
Runs after a tool call finishes, executing notifier.cjs. From juspay/shooter.
Stop
Runs when the agent finishes a response, executing notifier.cjs. From juspay/shooter.
PreToolUse
Runs before the agent uses a tool for Bash tool calls, executing dangerous_command_blocker.py and universal_hook_logger.py (2 commands). From circuit-synth/circuit-synth.
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing format_and_lint.sh. From supabase/supabase.