Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Hassaan146/forge-mentor/plugin install forgeWrote 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/hassaan146/forge-mentor/session-start)<a href="https://agentmods.dev/hooks/hassaan146/forge-mentor/session-start"><img src="https://agentmods.dev/badge/hooks/hassaan146/forge-mentor/session-start.svg" alt="Measured on agentmods" height="20"></a>Grade 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 6d 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": [
{
"hooks": [
{
"type": "command",
"command": "python \"${CLAUDE_PLUGIN_ROOT}/scripts/forge_update.py\" --hook",
"timeout": 15,
"_note": "The installed copy lagged the repository for four sessions running, and every one of them began by debugging the wrong build. Checks once a day, caches the answer outside the plugin so a reinstall does not reset it, and says nothing on any failure. FORGE_NO_UPDATE_CHECK=1 turns it off."
},
{
"type": "command",
"command": "python \"${CLAUDE_PLUGIN_ROOT}/scripts/reviewed.py\"",
"timeout": 15,
"_note": "The same check at the start of a session, because a review pulled in another window between sessions is the case a tool-matched hook cannot see."
},
{
"type": "command",
"command": "python \"${CLAUDE_PLUGIN_ROOT}/scripts/companion.py\"",
"timeout": 10,
"_note": "Brings ponytail in with Forge rather than leaving it in a routing table nothing is obliged to read (decision 059). One line when it is installed, the install command once per project when it is not, silence on every error and outside a Forge project. FORGE_NO_COMPANION=1 turns it off."
}
]
}
]
}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.
- 6d ago First seen · 26 lines scan A a4ab78f5b26e
SessionStart is a hook published in the GitHub repository Hassaan146/forge-mentor (22 stars, last pushed 20d 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
PreToolUse
Runs before the agent uses a tool for Bash, Edit and Write tool calls, executing dangerous-actions-blocker.sh via bash. From FlorianBruniaux/claude-code-ultimate-guide.
Stop
Runs when the agent finishes a response, executing index-sync-reminder.sh via bash. From FlorianBruniaux/claude-code-ultimate-guide.
SessionStart
Runs when a session starts, executing rtk-baseline.sh. From FlorianBruniaux/claude-code-ultimate-guide.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing arckit-codex-hook.mjs. From tractorjuice/arc-kit.
PreToolUse
Runs before the agent uses a tool for Edit, MultiEdit, Write and Bash tool calls, executing run-hook.cmd (2 commands). From rvdbreemen/adr-kit.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing run-hook.cmd. From rvdbreemen/adr-kit.