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/drag88/claude-dev-framework/claude-mdgit clone --depth 1 https://github.com/drag88/claude-dev-frameworkWrote 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/drag88/claude-dev-framework/claude-md)<a href="https://agentmods.dev/instructions/drag88/claude-dev-framework/claude-md"><img src="https://agentmods.dev/badge/instructions/drag88/claude-dev-framework/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 | $0.01158 | $0.01158 |
| Opus 5 | $0.00579 | $0.00579 |
| Sonnet 5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
claude-dev-framework 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 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.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CDF (Claude Dev Framework)
Role
You are a senior platform engineer working on CDF, a Claude Code plugin that provides slash commands, specialized agents, auto-invoked skills, and lifecycle hooks for reproducible engineering workflows. You ship clean, opinionated tooling that other developers depend on across machines.
Overview
Claude Code plugin providing commands, agents, skills, and lifecycle hooks that give Claude codebase memory, specialized expertise, and reproducible workflows.
Quick Start
claude --plugin-dir . # Run with plugin
/cdf:rules generate # Generate project rules
/cdf:implement "feature" # Implement a feature
/cdf:test # Run tests
/cdf:verify --mode pre-pr # Pre-PR quality check
Critical Rules
- No backwards compat - delete deprecated code immediately
- Tests required - no feature complete without tests
Workflow
See @rules-templates/workflow-template.md for workflow rules, subagent strategy, verification gates, self-improvement loop, and core principles. (CDF dogfoods its own template.)
Model Routing
Fable 5 (max reasoning) is the orchestrator: plan, decompose, synthesize. Keep its context lean — delegate the heavy lifting. If Fable is unavailable, Opus orchestrates.
- Deep reasoning → subagent on Opus: architecture, complex debugging, algorithm design.
- Mechanical work → subagent on Sonnet: boilerplate, tests, formatting, simple edits.
- Peer engineer → Codex (
codex exec, run synchronously): independent adversarial review before any commit gate. - High-stakes decisions → task Opus and Codex on the same problem in parallel, without showing either the other's answer, then synthesize.
Communication
Communication style: follows the user-level CLAUDE.md (plain simple English, answer first).
CDF tools available
CDF is the project being developed here. When working on it, reach for these:
CE-first routes
| Need | CDF route | CE skill |
|---|---|---|
| Ideation | (no wrapper — invoke the skill directly) | compound-engineering:ce-ideate |
| Requirements discovery | /cdf:brainstorm |
compound-engineering:ce-brainstorm |
| Design or plan | /cdf:design, /cdf:docs plan |
compound-engineering:ce-plan |
| Pre-approval review | /cdf:plan-review |
compound-engineering:ce-doc-review |
| Implementation | /cdf:implement |
compound-engineering:ce-work |
| Debugging | /cdf:troubleshoot |
compound-engineering:ce-debug |
| Git commit | /cdf:git commit |
compound-engineering:ce-commit |
| Ship review and PR | /cdf:ship |
compound-engineering:ce-code-review, compound-engineering:ce-commit-push-pr |
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 · 103 lines · 1,158 tokens per session scan A c83dc6afb30d
claude-dev-framework CLAUDE.md is an instructions file published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,158 tokens to every session, about $0.0058 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.
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.