agent/codex/IMPROVEMENTS.md
Snider e90a84eaa0 feat: merge go-agent + go-agentic + php-devops into unified agent repo
Combines three repositories into a single workspace:
- go-agent → pkg/orchestrator (Clotho), pkg/jobrunner, pkg/loop, cmd/
- go-agentic → pkg/lifecycle (allowance, sessions, plans, dispatch)
- php-devops → repos.yaml, setup.sh, scripts/, .core/

Module path: forge.lthn.ai/core/agent

All packages build, all tests pass.

Co-Authored-By: Virgil <virgil@lethean.io>
2026-03-06 15:23:00 +00:00

45 lines
1.9 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Codex Extension Improvements (Beyond Claude Capabilities)
## Goal
Identify enhancements for the Codex plugin suite that go beyond Claudes current capabilities, while preserving the Axioms of Life ethics modal and the blue-team posture.
## Proposed Improvements
1. **MCP-First Commands**
- Replace any shell-bound prompts with MCP tools for safe, policycompliant execution.
- Provide structured outputs for machinereadable pipelines (JSON summaries, status blocks).
2. **Ethics Modal Enforcement**
- Add a lint check that fails if prompts/tools omit ethics modal references.
- Provide a `codex_ethics_check` MCP tool to verify the modal is embedded in outputs.
3. **Strings Safety Scanner**
- Add a guardrail script or MCP tool to flag unsafe string interpolation patterns in diffs.
- Provide a “safe string” checklist to be autoinserted in risky tasks.
4. **CrossRepo Context Index**
- Build a lightweight index of core-agent plugin commands, scripts, and hooks.
- Expose a MCP tool `codex_index_search` to query plugin capabilities.
5. **Deterministic QA Runner**
- Provide MCP tools that wrap `core` CLI for Go/PHP QA with standardised output.
- Emit structured results suitable for CI dashboards.
6. **PolicyAware Execution Modes**
- Add command variants that default to “dryrun” and require explicit confirmation.
- Provide a `codex_confirm` mechanism for highimpact changes.
7. **Unified Release Metadata**
- Autogenerate a Codex release manifest containing versions, commands, and hashes.
- Add a “diff since last release” report.
8. **Learning Loop (NonSensitive)**
- Add a mechanism to collect nonsensitive failure patterns (e.g. hook errors) for improvement.
- Ensure all telemetry is optin and redacts secrets.
## Constraints
- Must remain EUPL1.2.
- Must preserve ethics modal and blueteam posture.
- Avoid shell execution where possible in Gemini CLI.