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/bolyra/bolyra/session-startgit clone --depth 1 https://github.com/bolyra/bolyraGrade B, and why
SessionStart scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
"command": "cd \"$CLAUDE_PROJECT_DIR\" 2>/dev/null && { echo '## identityos / Bolyra repo state'; echo; echo '### Recent commits'; git log --oneline -5 2>/dev/null; echo; echo '### Circuit build artifacts'; ls circuits/b What it actually says
{
"SessionStart": [
{
"hooks": [
{
"type": "command",
"command": "cd \"$CLAUDE_PROJECT_DIR\" 2>/dev/null && { echo '## identityos / Bolyra repo state'; echo; echo '### Recent commits'; git log --oneline -5 2>/dev/null; echo; echo '### Circuit build artifacts'; ls circuits/build/*_vkey.json 2>/dev/null | xargs -I{} basename {} | sort || echo '(no build artifacts)'; echo; echo '### Last test run'; [ -f .claude/last-test-run.log ] && tail -3 .claude/last-test-run.log || echo '(no test run logged yet)'; }; exit 0",
"timeout": 10
}
]
}
]
}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 · 13 lines scan B b2dbaedaa7f8
SessionStart is a hook published in the GitHub repository bolyra/bolyra (0 stars, last pushed yesterday), 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 B with 1 finding (reads agent configuration directories). 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 Edit, Write, Edit, Write and Bash tool calls, executing firewall-guard.sh, panic-guard.sh, dep-guard.sh, scope-guard.sh, todo-guard.sh, pre-tool-guard.py and pre-bash-guard.py with --show-current (8 commands). From InterCooperative-Network/icn.
SessionStart
Runs when a session starts on startup, resume, clear, fork, startup and compact, executing session-lifecycle.sh, hook-health.sh and session-orient.sh (4 commands). From InterCooperative-Network/icn.
PostToolUse
Runs after a tool call finishes for Edit, Write, Edit, Write, Edit, Write, MultiEdit, NotebookEdit and Bash tool calls, executing openapi-sync-guard.sh, post-tool-guard.py and session-lifecycle.sh (3 commands). From InterCooperative-Network/icn.
Stop
Runs when the agent finishes a response, executing session-lifecycle.sh. From InterCooperative-Network/icn.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing session-lifecycle.sh. From InterCooperative-Network/icn.
SessionEnd
Runs when a session ends, executing session-lifecycle.sh. From InterCooperative-Network/icn.