Codex Autoresearch is an autonomous, goal-driven experimentation CLI tool for Codex. It allows users to define a numeric target (e.g., reduce error count to zero) and then repeatedly runs a loop: the Codex model inspects the repo, makes one focused code change, the control script commits it, runs a verification command to measure the metric, keeps improvements or reverts failures, and appends audit events. The system supports both foreground (Codex Goal-driven) and background (detached controller with `codex exec` workers) modes, with strict state validation, atomic file operations, and Git-based rollback. Architecture: The codebase is split into three Python modules under `scripts/`—`autoresearch.py` (CLI and lifecycle orchestration), `autoresearch_core.py` (primitives for Git, command execution, event validation, and process management), and `autoresearch_report.py` (read-only rendering of history as terminal tables, TSV, or self-contained HTML). State is stored in `autoresearch-results/` as immutable `run.json` and append-only `events.jsonl`. The skill entrypoint is `SKILL.md`, which references three documentation files. The design emphasizes contract enforcement over silent recovery: malformed input, unexpected Git drift, or failed commands halt with precise diagnostics. The repository demonstrates high craftsmanship in defensive programming, strict JSON schema validation, atomic file writes, process tree management, and comprehensive unit/integration tests (including race condition testing for background controllers). It is a practical and well-documented example of building a reliable autonomous agent harness for codebases.
This repository implements an AI-agent skill that converts images, PDFs, and image-based PPT/PPTX files into fully editable PowerPoint (.pptx) documents. The system uses a deterministic CLI state machine (`editppt`) with a four-phase workflow: normalize input into per-page jobs, dispatch to subagents for page reconstruction, record page manifests, and finalize by rebuilding the PPTX from manifests. It integrates OCR (PaddleOCR or offline detector) for text bounding boxes, image generation/editing backends (built-in, OpenAI-compatible, or Codex OAuth), and LaTeX rendering for formulas. The output preserves native text boxes, shapes (including custom paths and polygons), tables, images, and speaker notes, with strict provenance tracking for all assets. The codebase is well-structured with clear separation of concerns, a manifest-driven assembly pattern, and comprehensive tests. However, the last commit date is anomalously in the future (2026-09-16), suggesting the repository may be abandoned or the timestamp is erroneous; combined with only 1 open issue and no recent activity, it is classified as stale. The technical drift is low as the code uses modern Python and standard libraries, but external dependencies (OCR, image APIs, LaTeX) may become incompatible over time.
The Codex Startup Pressure Test Skill is an npm package that installs a specialized skill for the OpenAI Codex AI assistant. Once installed, the skill enables users to pressure-test startup ideas by invoking it within Codex prompts, which then generates a structured evaluation covering verdict, scorecard, core assumptions, flaws, and actionable steps for validation. The architecture consists of a skill directory containing markdown-based instructions (SKILL.md and playbooks.md) that define the skill's behavior, an interface configuration for OpenAI (agents/openai.yaml), and an installer script (scripts/install.js) that handles deployment to the user's Codex skills directory. The skill relies on Codex's natural language processing to perform the actual analysis, with the repository providing the domain-specific guidance and framing. Key strengths include the well-documented skill framework that captures proven startup evaluation methodologies and the reusable installer script, which demonstrates solid CLI engineering practices with argument parsing, path handling, and recursive directory copying. The project is actively maintained and shows no signs of technical debt, depending only on Node.js built-in modules.