Claude Tools / Commands / rdf

Commands · rfxn/rdf

rdf

Governance-driven AI development — convention enforcement, quality gates, and typed agent personas for any repo

CLEARED_STATICagent-agnosticv3.6.3

Pipeline results

Coverage

CLEARED_STATIC

Tests run

13 / 15

Portability

Agent-agnostic (works beyond Claude)

Type

Commands

Tests & results

What the pipeline checked

TestStateResult or reason

eligibilityranall eligibility checks passed

dedupranunique -- no near-duplicate found

clocran78720 code lines / 319 files

secretsranno secret patterns matched

egressran10 lexical match(es) — FLAG-INFO (C-01: semantic analysis deferred to v2)

injectionranno patterns matched (confidence: STANDARD)

required-fieldsranrequired fields present: name, version, description

behaviouraldeferredbehavioural assessment deferred (v1): 58 shell file(s): ['lib/rdf_common.sh', 'state/rdf-state.sh', 'state/rdf-bus.sh']

semgrepran0 findings

banditran0 findings

detect-secretsran0 findings

skillspectorran166 findings

agnixran847 warnings

json-schemaranvalid=True schema=?

sc4-osvn/aSC4 live OSV lookup disabled for reproducibility; --no-llm verified network-free

What's inside

Components found

adapters/claude-plugin/output/agents/dispatcher.md

componentmedium

adapters/claude-plugin/output/agents/engineer.md

componentmedium

adapters/claude-plugin/output/agents/planner.md

componentmedium

adapters/claude-plugin/output/agents/qa.md

componentmedium

adapters/claude-plugin/output/agents/reviewer.md

componentmedium

adapters/claude-plugin/output/agents/uat.md

componentmedium

adapters/claude-plugin/output/commands/r-audit-slop.md

componentmedium

adapters/claude-plugin/output/commands/r-audit.md

componentmedium

adapters/claude-plugin/output/commands/r-build.md

componentmedium

adapters/claude-plugin/output/commands/r-context-audit.md

componentmedium

adapters/claude-plugin/output/commands/r-init.md

componentmedium

adapters/claude-plugin/output/commands/r-mode.md

componentlow

adapters/claude-plugin/output/commands/r-plan.md

componentmedium

adapters/claude-plugin/output/commands/r-refresh.md

componentmedium

adapters/claude-plugin/output/commands/r-review-answer.md

componentmedium

adapters/claude-plugin/output/commands/r-review.md

componentmedium

adapters/claude-plugin/output/commands/r-save.md

componentmedium

adapters/claude-plugin/output/commands/r-ship.md

componentmedium

adapters/claude-plugin/output/commands/r-spec.md

componentmedium

adapters/claude-plugin/output/commands/r-start.md

componentmedium

Coverage

Not assessed

behavioural execution not run
egress patterns logged (FLAG-INFO): 10 lexical match(es)

README

From the repository

# RDF -- rfxn Development Framework

[![CI](https://github.com/rfxn/rdf/actions/workflows/ci.yml/badge.svg)](https://github.com/rfxn/rdf/actions/workflows/ci.yml)
[![License: GPL v2](https://img.shields.io/github/license/rfxn/rdf?color=blue)](LICENSE)
[![Version](https://img.shields.io/github/v/release/rfxn/rdf?label=version&color=green)](https://github.com/rfxn/rdf/releases/latest)
![Adapters](https://img.shields.io/badge/adapters-6-purple.svg)
![Profiles](https://img.shields.io/badge/profiles-11-orange.svg)

**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, …

← Back to Commands