Instructions file CodexOpenCode
Instructions for ArdurAI/ardur-agent, covering ardur agent session instructions, mandatory bootstrap, source hierarchy, session ownership rule and parallel session conduct.
Agent
This document defines how Ardur Agent work is coordinated across LLM agents, human operators, and parallel coding sessions.
Skill Claude CodeCodex
Review a new or changed API surface against the contract concerns that bite later.
Skill Claude CodeCodex
Ground answers in retrieved user-corpus spans; cite every claim or refuse when retrieval is empty.
Skill Claude CodeCodex
Review a diff for correctness, security, and clarity issues.
Skill Claude CodeCodex
Systematically diagnose a failing test instead of guessing at fixes.
Skill Claude CodeCodex
Draft a Conventional-Commits message for a staged diff.
Skill Claude CodeCodex
Narrow down what made something slower using measurement, not intuition.
Skill Claude CodeCodex
Structure a new engineer's first week so they ship and build context, not just read.
Skill Claude CodeCodex
Restructure code without changing its behavior, one verifiable step at a time.
Skill Claude CodeCodex
Write a blameless postmortem that turns an incident into durable improvements.
Skill Claude CodeCodex
Turn an incident response into a reusable runbook the next on-call can follow.
Instructions file GitHub Copilot
Instructions for ArdurAI/ardur: See AGENTS.md in the repository root — it is the canonical, authoritative guide for agents working here, covering what Ardur does and does not claim, build and test commands, trust boundaries, and the contribution workflow.
Instructions file CodexOpenCode
Instructions for ArdurAI/ardur, covering ardur agent instructions, 0. first action in every new session, 1. what ardur is, and what it does not claim, 2. tl;dr commands and 3. architecture and trust boundaries.
Instructions file
Instructions for ArdurAI/ardur: This repository keeps a single, canonical set of agent instructions in AGENTS.md. This file exists only so that Claude Code loads them automatically; it deliberately holds no rules of its own, so that the two can never drift apart.
Instructions file Gemini CLI
Instructions for ArdurAI/ardur: This repository keeps a single, canonical set of agent instructions in AGENTS.md. This file exists only so that the Gemini CLI loads them automatically; it deliberately holds no rules of its own, so that the two can never drift apart.
Plugin Claude Code
Ardur runtime governance for Claude Code: mission-bound deny gating and signed Execution Receipts on tool calls.
Hook
Runs before the agent uses a tool, running an inline shell check. From ArdurAI/ardur.
Hook
Runs after a tool call finishes, running an inline shell check. From ArdurAI/ardur.
Hook
Runs when a tool call fails, running an inline shell check. From ArdurAI/ardur.
Hook
Runs when a subagent starts, running an inline shell check. From ArdurAI/ardur.
Hook
Runs when a subagent finishes, running an inline shell check. From ArdurAI/ardur.