agentmods.dev

hookstack: Hook for Claude Code

.claude/settings.json

SessionStart is a hook for Claude Code from steve-magne/hookstack. Its token cost is not measured, scanned A, a copy of SessionStart, MIT.

A group of checks that runs when an agent session starts or is compacted. It can load project and Git context, check dependencies, inspect branch state, load agent instructions, check staleness, and prepare the worktree environment.

In plain words
What is it for?
Use it at session startup to load instructions and GitHub context, check dependencies and stale information, warn about stashed work, and prepare the working environment.
Why use it?
It gives the agent current project context and surfaces repository or setup issues before work begins.

Hook for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable.

This is steve-magne/hookstack's own configuration. It tells Claude Code how to work on hookstack itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hookstack configures →

One of 26 entries in settings.json upstream. Installing this one merges just its entry into your config; the other 25 are separate, each on its own page.

not rated 7repo 5d ago A scan tokens not measured copy · 44% MIT
View source ↗ steve-magne/hookstack hookstack.app
Reuse

Borrowing it

Nothing to install: this file belongs to steve-magne/hookstack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/steve-magne/hookstack/main/.claude/settings.json
Clone the repo
git clone --depth 1 https://github.com/steve-magne/hookstack

Made for: Claude Code.

Wrote 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.

agentmods badge for SessionStart

README.md
[![agentmods](https://agentmods.dev/badge/hooks/steve-magne/hookstack/session-start/github.svg)](https://agentmods.dev/hooks/steve-magne/hookstack/session-start)
Your own site
<a href="https://agentmods.dev/hooks/steve-magne/hookstack/session-start"><img src="https://agentmods.dev/badge/hooks/steve-magne/hookstack/session-start/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for SessionStart

Your own site · 80×15
<a href="https://agentmods.dev/hooks/steve-magne/hookstack/session-start"><img src="https://agentmods.dev/badge/hooks/steve-magne/hookstack/session-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 44% copy Near-identical to another mod in the catalogue.
Security

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 1mo 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.

Origin

This is a copy

44% identical to SessionStart — 70 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/settings.json · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "SessionStart": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/load-git-context.mjs"
        },
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/setup-check-deps.mjs"
        },
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/session-start-pull-if-main.mjs"
        },
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/session-start-worktree-if-main.mjs"
        },
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/session-start-stash-warning.mjs"
        },
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/agents-md-loader.mjs"
        },
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/session-start-github-context.mjs"
        },
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/okf-staleness-check.mjs"
        }
      ]
    },
    {
      "hooks": [
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/setup-worktree-env.mjs",
          "statusMessage": "Copie des .env du worktree au démarrage de session..."
        },
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/worktree-create-update-deps.mjs",
          "statusMessage": "Mise à jour des dépendances du worktree..."
        },
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/setup-install-deps.mjs"
        }
      ],
      "matcher": "startup"
    },
    {
      "hooks": [
        {
          "type": "command",
          "command": "node $CLAUDE_PROJECT_DIR/.claude/hooks/reinject-after-compact.mjs"
        }
      ],
      "matcher": "com

Read the full file on GitHub · 77 lines

Same file

What else settings.json configures

This page is one entry in a file that holds 26. Installing the file brings all of them; each is measured and scanned on its own page.

Changes

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.

  1. 1mo ago First seen · 77 lines scan A c03a71a16097

Subscribe to this mod's changes

SessionStart is a hook published in the GitHub repository steve-magne/hookstack (7 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. It is 44% identical to SessionStart, differing in 70 lines, and is treated as a copy.

Claude Codeaiai-agentsanthropicclaudecli
Related

Other hooks, from other repositories

SessionStart

Runs when a session starts on startup, running echo '✓ plugin-development loaded: Use /plugin-development:i. From ivan-magda/claude-code-plugin-template.

ivan-magda/claude-code-plugin-template · not measured

PreToolUse

Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From apache/superset.

apache/superset · not measured

PreToolUse

Runs before the agent uses a tool, executing pre-write.sh and pre-bash.sh (2 commands). From anthropics/claude-cookbooks.

anthropics/claude-cookbooks · not measured

PostToolUse

Runs after a tool call finishes for Bash tool calls, executing hooks.sh via sh (3 commands). From anthropics/claude-plugins-official.

anthropics/claude-plugins-official · not measured

PreCompact

Runs before the context is compacted for manual and auto tool calls, executing hook-handler.cjs via node (4 commands). From ruvnet/RuView.

ruvnet/RuView · not measured

PreToolUse

Runs before the agent uses a tool for Bash tool calls, running node -e ". From heygen-com/hyperframes.

heygen-com/hyperframes · not measured