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/dbinky-skill-set/claude-mdgit clone --depth 1 https://github.com/dbinky/dbinky-skill-setWrote 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/instructions/dbinky/dbinky-skill-set/claude-md)<a href="https://agentmods.dev/instructions/dbinky/dbinky-skill-set/claude-md"><img src="https://agentmods.dev/badge/instructions/dbinky/dbinky-skill-set/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00570 | $0.00570 |
| Opus 5 | $0.00285 | $0.00285 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
dbinky-skill-set CLAUDE.md 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 4d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 43 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
PR Review Skill is a Claude Code plugin that orchestrates multi-persona PR reviews. It uses sequential AI agent personas (Architect, 10x Engineer, Security Expert, Engineering Manager, Senior Engineer) to debate and review pull requests, then lets users choose which fixes to implement.
This is a pure Markdown project — no build, test, or lint commands. All logic lives in Markdown instruction files that Claude interprets at runtime.
Architecture
Plugin entry: .claude-plugin/plugin.json declares the plugin; skills/pr-review/SKILL.md is the user-facing skill invoked via /pr-review.
Orchestrator (agents/review-orchestrator.md): The core engine. Handles GitHub CLI interactions, auto-detects languages/frameworks from PR diffs, loads applicable rule files, and dispatches agents sequentially through 7 phases:
- Pre-flight (gh CLI, auth, git remote)
- PR resolution (explicit number or auto-detect from branch)
- Language/framework detection → rule file selection
- Pipeline execution: Architect R1 → 10x R1 → Architect R2 → 10x R2 → Security → Manager
- Interactive fix selection (Must Fix / Should Fix / Consider / Defer tiers)
- Senior Engineer implementation of selected fixes
- Completion summary
Sequential execution is critical — each reviewer reads prior comments, enabling the architect-vs-pragmatist debate. This cannot be parallelized.
Agent personas (agents/*.md): Each file defines a reviewer's identity, comment format, tags, scope, and decision rules. Personas are instruction sets, not code.
Rule files (rules/languages/*.md, rules/frameworks/*.md): Technology-specific best practices split into general and security variants. Reviewers load only relevant rules based on detected tech. Languages: Go, Python, TypeScript, JavaScript, C#, Rust, Java, Dart. Frameworks: React, Angular, Flutter, Spring Boot, Orleans.
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.
- 4d ago First seen · 43 lines · 570 tokens per session scan A db0a8c6da503
dbinky-skill-set CLAUDE.md is an instructions file published in the GitHub repository dbinky/dbinky-skill-set (5 stars, last pushed 2mo ago), licensed MIT. It adds 570 tokens to every session, about $0.0029 per session on Opus 5. 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 2026-08-31.
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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.