RDF — rfxn Development Framework

RDF -- rfxn Development Framework

Governance-driven AI development for teams that ship to production.

RDF is a convention governance layer for AI coding agents. It sits between the human and the AI runtime (Claude Code, Codex, Antigravity CLI — plus Gemini CLI legacy), encoding project conventions, quality gates, and domain expertise into typed agent personas -- so the AI writes code that actually follows your rules.

Drop it on any repo. /r-init auto-detects your stack and scaffolds governance, quality gates, and typed agent personas -- no rfxn context required. Battle-tested on production security tooling (APF, LMD, BFD), built to generalize. The value is the pattern: governance-driven agents, adversarial quality gates, convention inheritance, and context-window management. Issues and PRs welcome -- support is best-effort and community-driven. Quickstart: your repo in 5 minutes ->

---

Real recorded session: install RDF, initialize a plain Flask project, verify health — 42 seconds, no edits.

---

1. How It Works

Six universal agents handle every project. Their behavior is shaped by governance files initialized per-project -- not baked into prompts. A QA agent reviewing a bash firewall tool and a QA agent reviewing a Python pipeline follow different rules because their governance files are different, not because they are different agents.

---

2. Quick Start

# ── Option A: plugin install (consumer — commands namespaced /rdf:r-*) ──
#   In Claude Code:
#     /plugin marketplace add rfxn/rdf
#     /plugin install rdf@rdf
#   Note: hooks + status line require jq on PATH.

# ── Option B: symlink deploy (contributor/power mode — bare /r-*) ──
# 1. Clone
git clone https://github.com/rfxn/rdf.git && cd rdf

# 2. Generate adapter output for your AI tool
bin/rdf generate claude-code          # or: claude-plugin, codex, antigravity, agent-skills, agents-md, gemini-cli (legacy), all

# 3. Deploy (symlinks -- regeneration auto-updates)
bin/rdf deploy claude-code            # or: bin/rdf deploy gemini-cli

# 4. Initialize a project with governance
cd /path/to/your/project
/r-init                               # auto-detects project type, suggests profiles

That's it. Your AI agent now has project-specific governance, quality gates, and domain expertise.

Verify:

bin/rdf doctor                        # health check: artifacts, drift, sync

New to RDF? The 5-minute quickstart walks this path on a plain Flask project, with real output at every step.

---

3. Configuration

Environment Variables

Variable	Default	Purpose
RDF_HOME	resolved from bin/rdf	RDF install root (canonical/, lib/, bin/, state/)
RDF_CANONICAL	$RDF_HOME/canonical	Canonical content source tree
RDF_TARGET	~/.claude	Deploy target for claude-code adapter

Most users do not need to override these — bin/rdf resolves paths from its own location automatically. Overrides matter only for multi-install setups or CI runs against a fixture tree.

Per-Project Setup

cd /path/to/project
/r-init                               # auto-detects profiles, generates governance

rdf init creates (inside the target project):

Path	Purpose
CLAUDE.md	Project working instructions (typically excluded from commits)
.rdf/governance/	conventions, constraints, verification, anti-patterns, architecture
.rdf/memory/MEMORY.md	Session-persistent project facts
.git/info/exclude entries	Working-file exclusions (CLAUDE.md, PLAN*.md, .rdf/, etc.)

Convention Inheritance

The most specific rule wins:

project CLAUDE.md   >   workspace CLAUDE.md   >   profile defaults   >   core defaults

Agents read the chain at session start and apply it hierarchically. A project CLAUDE.md rule overrides a profile default; a workspace CLAUDE.md rule overrides core.

Deployment Model

Emergency edits (direct changes to ~/.claude/) are permitted but must be pulled back to canonical via rdf sync. Drift is detected by rdf doctor --scope content-drift using per-file .rdf-hash sidecars.