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/c3-oss/codexcw/session-startgit clone --depth 1 https://github.com/c3-oss/codexcwGrade 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": "printf '\\n=== c3-oss/codexcw ===\\n- Canonical guide: AGENTS.md (read it before substantial changes).\\n- Polyglot monorepo: Go at the root; Rust core in crates/codexcw; npm + PyPI in bindings/{node,python}.\\n- Toolchain: devbox + just (recipes are language-namespaced: go-*, rust-*, node-*, py-*).\\n- Usage examples: docs/examples/{go,rust,typescript,python}.md.\\n- Conventional Commits with required scope are enforced by commitlint.\\n- Local CI lane: `just ci`.\\n===\\n\\n'",
"timeout": 5
}
]
},
{
"matcher": "resume",
"hooks": [
{
"type": "command",
"command": "printf '\\n=== c3-oss/codexcw ===\\n- Canonical guide: AGENTS.md (read it before substantial changes).\\n- Polyglot monorepo: Go at the root; Rust core in crates/codexcw; npm + PyPI in bindings/{node,python}.\\n- Toolchain: devbox + just (recipes are language-namespaced: go-*, rust-*, node-*, py-*).\\n- Usage examples: docs/examples/{go,rust,typescript,python}.md.\\n- Conventional Commits with required scope are enforced by commitlint.\\n- Local CI lane: `just ci`.\\n===\\n\\n'",
"timeout": 5
}
]
}
]
}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 · 24 lines scan A 7c16b6c3abdb
SessionStart is a hook published in the GitHub repository c3-oss/codexcw (1 stars, last pushed yesterday), licensed CC0-1.0. 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 2026-08-31.
Other hooks, from other repositories
SessionStart
Runs when a session starts, executing bootstrap.sh via sh. From svyatov/handrail.
PreToolUse
Runs before the agent uses a tool for Bash tool calls, executing commit-gate.sh. From AndrewDryga/emisar.
PostToolUse
Runs after a tool call finishes for Bash tool calls, executing post-tool-use.js via node. From Davidcreador/codex-token-guard.
PostCompact
Runs after the context is compacted for ^(auto and manual)$ tool calls, executing launch.py via python3. From hehee9/codex-compressor.
Stop
Runs when the agent finishes a response, executing hook-orchestrator.mjs via node. From tellang/triflux.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing ingest-turn.sh and prompt-recall.sh via bash (2 commands). From Principle-Labs/Corivo.