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/sirsjg/flux/session-startgit clone --depth 1 https://github.com/sirsjg/fluxGrade 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": "flux ready --json"
}
]
}
]
}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 3b03d3aaded9
SessionStart is a hook published in the GitHub repository sirsjg/flux (98 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
PostToolUse
Runs after a tool call finishes for task_claim, mcp__.*__task_claim, task_deliver, mcp__.*__task_deliver, task_release, mcp__.*__task_release, task_deliver and mcp__.*__task_deliver tool calls, executing claim-guard.mjs and post-deliver.mjs via node (2 commands). From ustoppble/overclick.
PreToolUse
Runs before the agent uses a tool for task_create and mcp__.*__task_create tool calls, executing pre-create.mjs and claim-guard.mjs via node (2 commands). From ustoppble/overclick.
SessionStart
Runs when a session starts on startup, resume, clear and compact, executing session-start.mjs via node. From ustoppble/overclick.
Stop
Runs when the agent finishes a response, executing stop-guard.mjs via node. From ustoppble/overclick.
PostToolUse
Runs after a tool call finishes for .*chorus_pm_submit_proposal, .*chorus_submit_for_verify and .*chorus_admin_verify_task tool calls, executing on-post-submit-proposal.sh, on-post-submit-for-verify.sh and on-post-verify-task.sh (3 commands). From Chorus-AIDLC/Chorus.
PreToolUse
Runs before the agent uses a tool for EnterPlanMode, ExitPlanMode and Task tool calls, executing on-pre-enter-plan.sh, on-pre-exit-plan.sh and on-pre-spawn-agent.sh (3 commands). From Chorus-AIDLC/Chorus.