Instructions file CodexOpenCode
Instructions for itdojp/ae-framework, covering agents — ae-framework router, decision table, invariants(不変条件), progressive disclosure(参照順) and scope.
Instructions file CodexOpenCode
Instructions for itdojp/ae-framework, covering agents — ae-framework router, decision table, invariants(不変条件), progressive disclosure(参照順) and scope.
Instructions file
Instructions for itdojp/ae-framework, covering claude — ae-framework router, read order, role boundary, invariants and scope.
Agent
This matrix defines how producer output enters the ae-framework assurance control plane. Producers can generate code, review comments, raw logs, test results, or tool responses. ae-framework does not treat those outputs as trusted by default; it normalizes them into contract-backed artifacts that reviewers, policy…
Agent
Agent "agents-doc-boundary-matrix" from itdojp/ae-framework, covering agent documentation boundary matrix, english, boundary definitions (primary / secondary), writing rules (drift prevention) and checks when changing these docs.
Agent
Agent "ci" from itdojp/ae-framework, covering agents runbook: ci, english, when to use, what to load (primary sources) and commands (copy/paste).
Agent
A catalog of slash commands for pull requests and issues in GitHub, including commands for reviews, testing, security checks, performance checks, formal verification, and workflow dispatches.
Agent
The commands below are the current operator baseline. Start with the focused validator, then re-run verify:lite.
Agent
Evidence adapters describe how raw producer output from coding agents and humans is routed into ae-framework judgment artifacts. They do not control agents, approve changes, or assert that an agent was correct. Their job is to collect enough contract-backed evidence for review, policy gates, handoff, and release…
Agent
Agent "formal" from itdojp/ae-framework, covering agents runbook: formal methods, english, when to use, what to load (primary sources) and commands (copy/paste).
Agent
This document defines the minimum handoff protocol between agents. It does not replace the detailed summary in a Change Package. When a Change Package exists, reference it from the handoff instead of duplicating that detail.
Agent
This is the minimal adapter that normalizes existing CI and evidence artifacts into short feedback that Claude Code and Codex can feed back into the next continuation step without manual reshaping.
Agent
This document is the SSOT for safe use of spawnagent and subagents in this repository. Its purpose is to prevent unexpected edits, commits, or branch mutations from leaking into a shared branch or shared worktree.
Agent
Agent "pr" from itdojp/ae-framework, covering agents runbook: pull request, english, when to use, what to load (primary sources) and commands (copy/paste).
Agent
Agent "security" from itdojp/ae-framework, covering agents runbook: security, english, when to use, what to load (primary sources) and commands (copy/paste).
Agent
Agent "spec" from itdojp/ae-framework, covering agents runbook: spec, english, when to use, what to load (primary sources) and commands (copy/paste).
Agent
The Code Generation Agent is a Phase 4 component of the ae-framework that automatically generates implementation code from tests and specifications. It follows the TDD principle of writing minimal code to make tests pass, then refactoring for quality.
Agent
The Formal Agent is a critical component of the ae-framework that bridges Phase 1 (Intent) and Phase 3 (Tests) by converting requirements into formal, verifiable specifications. It provides comprehensive capabilities for generating, validating, and model-checking formal specifications across multiple notations and…
Agent
The Intent Agent is a core component of the ae-framework Phase 1, responsible for requirements gathering, analysis, and intent extraction from multiple sources. It transforms raw requirements into structured formats that feed into subsequent phases of the architectural engineering process.
Agent
The Operate Agent is the final phase in the ae-framework's 6-phase cycle (Intent→Formal→Tests→Code→Verify→Operate). It handles production operations, monitoring, and optimization to ensure deployed systems run reliably, efficiently, and securely.
Agent
The Verify Agent is a comprehensive verification and quality assurance system for Phase 5 of the ae-framework. It provides automated verification capabilities including testing, coverage analysis, code quality checks, security scanning, and compliance validation.