Skip to content
Agentmart
Submit a tool

BuildHook

Create and validate module hooks.

Skill by N4M3Z

IndexedEUPL-1.2★ 4
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/n4m3z-buildhook

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Create and validate module hooks. USE WHEN create hook, new hook, write hook, scaffold hook, validate hook, check hook, hook conventions, hook events, hook structure.

Use cases: writing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/buildhook

What's inside

Skill name
BuildHook
Description
Create and validate module hooks. USE WHEN create hook, new hook, write hook, scaffold hook, validate hook, check hook, hook conventions, hook events, hook structure.
License
EUPL-1.2
Instructions
226 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed

Files (1)

  • SKILL.md

SKILL.md (first lines)

# BuildHook

Create and validate hook scripts for forge modules. Hooks are bash scripts triggered by Claude Code events, routed through the `dispatch` binary.

## Workflow Routing

| Workflow     | Trigger                                       | Section                                  |
|--------------|-----------------------------------------------|------------------------------------------|
| **Create**   | "create hook", "new hook", "scaffold hook"    | [Create Workflow](#create-workflow)       |
| **Validate** | "validate hook", "check hook"                 | [Validate Workflow](#validate-workflow)   |

## Hook Conventions

### Design Principles

Hooks must block or inject, never advise. A hook that "reminds" or "nudges" is a rule or skill in disguise. Before proposing a hook, check whether Claude Code already injects this context: rules are always loaded, skills are auto-discovered; don't duplicate what the runtime provides. Kill test: if a hook breaks silently and nobody notices for a month, it wasn't worth shipping. See [ARCH-0011](../../docs/decisions/ARCH-0011 Hook Design Principles.md) for the full design criteria.

### Events and Output Modes

Every hook handles one of 9 Claude Code events. Each event has a fixed output mode that determines how module output is handled:

| Event              | Mode        | Behaviour                                              |
|--------------------|-------------|--------------------------------------------------------|
| `SessionStart`     | Concatenate | All module outputs combined and emitted to AI context  |
| `PreCompact`       | Concatenate | All module outputs combined and emitted to AI context  |
| `PreToolUse`       | Gate        | Exit 2 blocks the tool call; exit 0 allows             |
| `Stop`             | Gate        | Exit 2 blocks session exit; exit 0 allows              |
| `SubagentStop`     | Gate        | Exit 2 blocks subagent exit; exit 0 allows             |
| `PostToolUse`      | Passive     | Output discarded; runs for side effects only           |
| `SessionEnd`       | Passive     | Output discarded; runs for side effects only           |
| `UserPromptSubmit` | Passive     | Output discarded; runs for side effects only           |
| `Notification`     | Passive     | Output discarded; runs for side effects only           |

### Output Mode Decision Table

Use this when choosing which event to hook:

| Goal                                  | Event            | Mode        | Notes                                  |
|---------------------------------------|------------------|-------------|----------------------------------------|
| Inject context at session start       | `SessionStart`   | Concatenate | Emit markdown to stdout                |
| Block a tool call (access control)    | `PreToolUse`     | Gate        | Exit 2 to block, 0 to allow           |
| Enforce rules before exit             | `Stop`           | Gate        | Exit 2 to block, 0 to allow           |
| React to a tool result                | `PostToolUse`    | Passive     | Side effects only, output discarded    |
| Clean up after session                | `SessionEnd`     | Passive     | Side effects only, output discarded    |
| Inject context before compaction      | `PreCompact`     | Passive     | Emit markdown to stdout                |

### File Naming

Hook scripts use **PascalCase** matching the event name:

| Event            | Filename                |
|------------------|-------------------------|
| `SessionStart`   | `hooks/SessionStart.sh` |
| `PreToolUse`     | `hooks/PreToolUse.sh`   |
| `PostToolUse`    | `hooks/PostToolUse.sh`  |
| `Stop`           | `hooks/Stop.sh`         |
| `PreCompact`     | `hooks/PreCompact.sh`   |

### Dual-Mode Preamble

Every hook script starts with this template. It resolves the module root from either forge-core dispatch or standalone plugin context:

```bash
#!/usr/bin/env bash
set -euo pipefail

MODULE_ROOT="${FORGE_MODULE_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(command cd "$(dirname "$0")/.." && pwd)}}"
```

### Stdin JSON

Claude Code pipes a JSON payload to hook scripts on stdin. The schema varies by event:

- **PreToolUse / PostToolUse**: `{"tool_name":"...", "tool_input":{...}}`
- **Stop**: `{"stop_reason":"...", ...}`
- **SessionStart**: empty or `{}`

Read stdin once: `INPUT=$(cat)`. Parse with `yq -p json` or a compiled binary.

### Windows

Claude Code on Windows requires Git for Windows, which provides Git Bash. Plugin hooks run in Git Bash, not PowerShell or cmd. Write hooks as standard bash scripts; they work cross-platform without `.cmd` or `.ps1` wrappers. Platform detection inside a hook when needed: `$OS == "Windows_NT"`.

### Registration Chain

For dispatch to find a hook:

1. Hook file exists at `hooks/<EventName>.sh` and is executable
2. `module.yaml` lists the event in `events:` (Tier 1 check)
3. Module is listed in project `defaults.yaml` under `modules:` (Tier 0)

The 3-tier event check: `config.yaml` override (authoritative) > `module.yaml` events > hook file existence (fallback).

### Exit Code and Output Contract

Claude Code distinguishes three exit classes ([hooks reference][CCHOOKS]): exit 0 (success; stdout is parsed for JSON control fields), exit 2 (blocking error; stdout is ignored, stderr is fed back, and whether it blocks depends on the event), and any other code (non-blocking error; the action proceeds). The trap: `exit 1` blocks nothing despite being the conventional Unix failure code.

Forge hooks block via exit 0 plus stdout JSON rather than exit 2: a structured decision carries its reason through the documented protocol and cannot be confused with an infrastructure failure.

- Empty stdout = allow
- `{"decision":"block","reason":"..."}` = block
- `{"hookSpecificOutput":{"additionalContext":"..."}}` = context injection

Guard files use `$PPID` or `$SESSION_ID` scoping to prevent repeat firing within a session. Hooks that cannot build or run must exit 0 (graceful degradation: never block Claude on infrastructure failure).

[CCHOOKS]: https://code.claude.com/docs/en/hooks

---

## Create Workflow

### Step 1: Determine event and output mode

Ask the user:
1. What should trigger this hook? (Use the Output Mode Decision Table above)
2. What should the hook do? (Inject context, block an action, or run a side effect?)

### Step 2: Scaffold the hook script

From N4M3Z/forge-core, EUPL-1.2.

More from N4M3Z/forge-core

Signals

Stars
4
Forks
3
Open issues
8
Last commit (this folder)
Jun 16, 2026 (4 months ago)
Last release
Apr 16, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
EUPL-1.2
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from N4M3Z

Cite this page

BuildHook skill. Agent Mart. https://agentmart.dev/skills/n4m3z-buildhook (last updated 2026-10-24)