Investigate LazyCodex and Codex bugs using reproduction results and source code. Identify the responsible repository, then prepare or submit an English GitHub report with evidence, likely causes, fix guidance, and a verification plan.
Retrieve pages blocked by web access filters, read Chinese and social platforms through dedicated tools, and inspect archived copies with their dates. Escalate to browser interaction when simpler extraction methods cannot provide the needed content.
Cleans redundant comments, dead code, duplication, and unnecessary complexity from branch changes or selected files. Establishes passing regression tests first, then checks that cleanup preserves existing behavior and public APIs using the project's quality tools.
Finds and rewrites code by its syntax structure across 25 languages. Use it to locate matching calls or declarations, preview bulk changes, and run reusable YAML rules that check code or apply fixes.
Automate forms, clicks, screenshots, and website checks in a browser where you are already signed in. A separately launched browser also supports scraping and network capture, while login or verification steps can be handed to a person.
Analyze CSV, Parquet, and JSON files to answer questions through grouping, joins, cleaning, time series, and charts. Chooses DuckDB or Polars and a suitable processing location based on the task and available memory.
Checks LazyCodex and Codex CLI installations against current source code, inspecting versions, settings, plugin files, and runtime behavior. Produces an evidence-backed health report with suggested fixes while leaving the installed setup unchanged.
Investigate LazyCodex and Codex bugs using reproduction results and source code. Identify the responsible repository, then prepare or submit an English GitHub report with evidence, likely causes, fix guidance, and a verification plan.
Set up a language server, a tool that helps agents understand source code, for a project. Detect the language, install and configure the server, then verify that it responds to a diagnostic request.
Use language servers, tools that understand code structure, to check errors, locate definitions, and find references in Codex. Check whether a symbol can be renamed and apply the rename across the workspace.
Reviews completed changes against the original goal, constraints, code quality, and security. Combines hands-on checks of the actual application or API with recorded evidence, then reports blockers and a passed, failed, or inconclusive verdict.
Understand how Codex Rules adds project instructions and file-specific rules to agent context. Check supported rule locations, when rules are applied, and environment settings for modes, sources, and text limits.
Coordinates a named team of Codex workers with concrete responsibilities and shared progress records. It selects available collaboration tools, manages communication and separate working copies when needed, and handles integration, team archival, and cleanup after the work ends.
Retrieve pages blocked by web access filters, read Chinese and social platforms through dedicated tools, and inspect archived copies with their dates. Escalate to browser interaction when simpler extraction methods cannot provide the needed content.
Carry development tasks through implementation and verification on the actual interface, such as a browser, terminal, or API. Define success criteria upfront, scale checks to the change, and retain evidence and progress notes.
Checks the visual quality of web pages, terminal interfaces, and paginated documents. Uses phone and desktop captures, light and dark themes, and an Apple design checklist to produce screenshot evidence and item-by-item verdicts.
Reproduce and fix LazyCodex or Codex defects in a temporary workspace. Verify the change with regression tests and real usage, then deliver an upstream Codex pull request or a LazyCodex issue containing the tested patch.
Help Codex respond to automatic warnings about comments after code edits. It explains when the checker runs and directs Codex to fix the flagged comment or explain it before continuing with other work.
Search local session histories across Codex, Claude Code, OpenCode, and other coding agents. Find earlier requests, inspect transcripts and child sessions, and reconstruct past work using recorded evidence, with filters for dates, projects, platforms, and models.
Investigate crashes, hangs, incorrect responses, and other failures by testing hypotheses against observed runtime behavior. Confirm the cause, verify the fix with a reproducing test, check the real workflow, and remove temporary debugging artifacts.
Builds and refines web pages and components using documented design rules. Covers layout, styling, animation, and reusable components, with browser-based checks for visual quality, performance, accessibility, and SEO.
Manage Git changes and investigate repository history with evidence from commands. Group related edits into focused commits, reorganize branch history when requested, trace changes, and identify the first faulty commit when a repeatable check is available.
Create or update hierarchical AGENTS.md files that explain a project's structure, commands, and conventions. Analyze directory complexity to choose useful locations, then keep local guidance concise and avoid repeating parent instructions.
Refactor code through a staged process that maps dependencies, assesses test coverage, and plans small changes. Use it to extract functions, simplify code, or restructure modules while checking tests and diagnostics throughout.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)