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 instructions/dbinky/pommel/claude-mdgit clone --depth 1 https://github.com/dbinky/PommelWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02561 | $0.02561 |
| Opus 5 | $0.01281 | $0.01281 |
| Sonnet 5 | $0.00512 | $0.00512 |
| Haiku 4.5 | $0.00256 | $0.00256 |
Grade C, and why
Pommel CLAUDE.md scanned grade C with 2 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 3d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/dbinky/Pommel/main/scripts/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/dbinky/Pommel/main/scripts/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Pommel is a local-first semantic code search system designed to reduce context window consumption for AI coding agents. It maintains an always-current vector database of code embeddings, enabling targeted semantic searches instead of reading numerous files into context.
Status: v0.7.3 - Configurable timeouts for cold starts and slow connections
Code Search Priority
IMPORTANT: Use pm search BEFORE using Grep/Glob for code exploration.
When looking for:
- How something is implemented →
pm search "authentication flow" - Where a pattern is used →
pm search "error handling" - Related code/concepts →
pm search "database connection" - Code that does X →
pm search "validate user input"
Only fall back to Grep/Glob when:
- Searching for an exact string literal (e.g., a specific error message)
- Looking for a specific identifier name you already know
- Pommel daemon is not running
Example workflow:
# First: semantic search to find relevant code
pm search "retry logic with backoff" --limit 5
# Then: read the specific files/lines returned
# Only use grep if you need exact string matching
Quick Start
# Initialize Pommel in a project
pm init --auto --claude --start
# Search the codebase semantically
pm search "database connection handling"
pm search "error handling patterns" --limit 5
pm search "CLI command setup" --json
# Check status
pm status
# Reindex after major changes
pm reindex
Architecture
AI Agent / Developer
│
▼
Pommel CLI (pm) ──────► search, status, init, start, stop, reindex, config
│
▼
Pommel Daemon (pommeld)
├── File watcher (fsnotify, debounced)
├── Tree-sitter chunker (AST-aware)
└── Embedding generator (Ollama client)
│
▼
SQLite + sqlite-vec (local vector DB)
▲
│
Jina Code Embeddings via Ollama (768-dim vectors)
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.
- 3d ago First seen · 324 lines · 2,561 tokens per session scan C 788a76a200f2
Pommel CLAUDE.md is an instructions file published in the GitHub repository dbinky/Pommel (110 stars, last pushed 5mo ago), licensed MIT. It adds 2,561 tokens to every session, about $0.0128 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.