agentmods.dev

semble-hooks CLAUDE.md

semble-hooks CLAUDE.md is an instructions file for coding agents from benediktkraus/semble-hooks. It costs 984 tokens per session, scanned A, original, Apache-2.0.

Project instructions for hooks that search a codebase and add relevant code to an AI coding assistant’s prompt. A hook is an automated action triggered by an event such as submitting a prompt or starting a session.

In plain words
What is it for?
Use it when working on Semble-based code search hooks, configuration loading, debug logs, or integrations with Claude Code, Codex, Gemini, and OpenClaw.
Why use it?
It helps the assistant see code related to the request instead of relying only on the user’s short description.

Instructions file

not rated 2 3mo ago A scan 984 tokens original Apache-2.0
View the source file benediktkraus/semble-hooks
Install

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.

agentmods
npx agentmods add instructions/benediktkraus/semble-hooks/claude-md
Clone the repo
git clone --depth 1 https://github.com/benediktkraus/semble-hooks

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 semble-hooks CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/benediktkraus/semble-hooks/claude-md.svg)](https://agentmods.dev/instructions/benediktkraus/semble-hooks/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/benediktkraus/semble-hooks/claude-md"><img src="https://agentmods.dev/badge/instructions/benediktkraus/semble-hooks/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 984 This file is loaded in full into every session.
When invoked 984 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00984 $0.00984
Opus 5 $0.00492 $0.00492
Sonnet 5 $0.00197 $0.00197
Haiku 4.5 $0.00098 $0.00098

Measured 5d ago against content hash 0ac6ca56957f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

semble-hooks CLAUDE.md scanned grade A 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 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Native child_process (execFileSync mit Array-Args)
CLAUDE.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semble Hooks — CLAUDE.md

Was ist das

Code-Intelligence Hooks für AI Coding CLIs. Bei jedem Prompt wird Semble CLI aufgerufen, relevante Code-Chunks werden als <relevant-code> Block in den Agent-Context injiziert. Parallel zu DREVIHO (Memory Hooks), eigenes Repo.

Projekt-Typ

open-source

Tech-Stack

  • Node.js >= 18 (ESM, .mjs, keine npm Dependencies)
  • Semble CLI v0.2.0 (semble search "query" [path] -k N) — Python, CPU-only, potion-code-16M
  • Native child_process (execFileSync mit Array-Args)
  • Hook-Systeme: Claude Code UserPromptSubmit/SessionStart, Codex hooks.json, Gemini hooks.json, OpenClaw Plugin (before_prompt_build)

Architektur-Referenz

DREVIHO Repo (ehemals openviking-hooks): https://github.com/benediktkraus/dreviho

  • scripts/auto-recall.mjs — Hook-Pattern (stdin JSON → stdout decision + additionalContext)
  • scripts/config.mjs — Multi-Agent Config Loader
  • scripts/debug-log.mjs — JSON Lines Logger
  • install.sh — Multi-CLI Installer

Entscheidungen

  • [2026-05-21]: Eigenes Repo statt in DREVIHO integriert — saubere Trennung Code vs Memory
  • [2026-05-21]: Semble CLI Call via execFileSync, kein MCP Server, kein Daemon — Security + Einfachheit
  • [2026-05-22]: Standalone Config statt DREVIHO Scope-Resolver — Public Repo muss ohne OV funktionieren
  • [2026-05-22]: Output-Tag <relevant-code> — klare Unterscheidung zu DREVIHOs <relevant-memories>
  • [2026-05-22]: SessionStart = Warmup Search — Semble v0.2.0 hat keinen Index-Befehl, cached on-the-fly
  • [2026-05-22]: Config unter ~/.semble-hooks/config.json — eigener Namespace, kein OV-Dependency
  • [2026-05-22]: Lizenz Apache-2.0 — permissive, Patent Grant
  • [2026-05-22]: Node.js ESM (.mjs), kein TypeScript, kein Build-Step — minimale Dependencies
  • [2026-05-25]: OpenClaw Plugin via before_prompt_build Hook — gleiche Tiefe wie OpenViking-Enhanced

Regeln

  • Kein execSync — nur execFileSync mit Array-Args
  • Keine hardcoded Pfade — Config oder Defaults
  • Keine npm Dependencies — nur Node.js built-ins
  • Code-Chunks als <relevant-code> Tag (nicht <relevant-memories>)
  • Graceful degradation: wenn semble nicht installiert → leerer Output, kein Error

Read the full file on GitHub · 64 lines

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. 5d ago First seen · 64 lines · 984 tokens per session scan A 0ac6ca56957f

Subscribe to this mod's changes

semble-hooks CLAUDE.md is an instructions file published in the GitHub repository benediktkraus/semble-hooks (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 984 tokens to every session, about $0.0049 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsai-toolsclaude-codecode-intelligencecode-searchcodexgemini-cli
Related

Other instructions, from other repositories

Repo-Interrogator AGENTS.md

AGENTS.md instructions for taggedzi/Repo-Interrogator, covering agents.md, agent instructions, python environment, 0) decision hierarchy (important) and 0.5) architectural decision records (adrs).

taggedzi/Repo-Interrogator · 2,111 tokens

Repo-Interrogator CLAUDE.md

Claude Code instructions for taggedzi/Repo-Interrogator, covering claude.md, project overview, environment setup, developer install and commands.

taggedzi/Repo-Interrogator · 1,658 tokens

repobrain copilot-instructions.md

Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.

study8677/repobrain · 229 tokens

CodeNib AGENTS.md

AGENTS.md instructions for sysevol-ai/CodeNib, covering agents.md, layered objectives, storage scope guard, dev commands and git, commit, and pr rules.

sysevol-ai/CodeNib · 2,702 tokens

mcpls copilot-instructions.md

Copilot instructions for bug-ops/mcpls, covering copilot instructions for mcpls, type safety, idiomatic rust, architecture and async.

bug-ops/mcpls · 1,148 tokens

sourcebot CLAUDE.md

Claude Code instructions for sourcebot-dev/sourcebot, covering claude code guidelines, database migrations, building packages, backend workloads and execution locks.

sourcebot-dev/sourcebot · 4,674 tokens