Skill Claude CodeCodex
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
Skill Claude CodeCodex
CI-runner adaptation of the code-review skill. Applies code-review's lenses and severity rubric to a pull request inside a CI job, where the runner handles PR discovery, posting, and thread resolution and findings stream out as JSONL. Use when a CI runner drives the review.
Skill Claude CodeCodex
Find and watch a GitHub pull request for review findings, investigate each finding, fix and push legitimate issues, and stop once checks are green and review threads are resolved. Use when asked to watch, monitor, poll, babysit, or keep checking a PR for review comments or automated review feedback.
Skill Claude CodeCodex
Code review a pull request or the current working changes with independent reviewer lenses, validated findings, and severity-rated results. Establishes a branch and a draft pull request when none exists yet. Accepts an effort level, an optional fix mode that applies the smallest complete correction for each confirmed…
Skill Claude CodeCodex
Strictly review the branch's changes for reuse, simplification, abstraction quality, and maintainability, then fix the issues. An ambitious code-quality pass that hunts for structural simplifications (code-judo moves), giant files, and spaghetti-condition growth.
Skill Claude CodeCodex
Coordinate one authorized task across a bounded collection of local repositories and caller-selected existing user-level installations while preserving unrelated work. Use when a task spans repositories, when repository-neutral changes must remain converged, or when propagation must also update matching editable local…
Skill Claude CodeCodex
Run the multi-subagent code-review workflow at high effort with fix mode, repair and retry failed checks until they pass, then ready, squash-merge, and verify the current pull request.
Skill Claude CodeCodex
Keep repository publishing metadata generic and isolated. Use when a user requests generic delivery metadata, invokes generic-push, or applies generic publishing rules across multiple repositories.
Skill Claude CodeCodex
Compare, grade, rate, rank, or choose between two implementation plans written for the same goal or original agent prompt. Use when the user invokes /grade-plans followed by a goal or asks for a consistent evidence-based comparison of two plans, including weighted scores, strengths, weaknesses, a winner or tie, and…
Skill Claude CodeCodex
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
Skill Claude CodeCodex
List the pull request URLs for every currently open pull request changed during the entire current session, including drafts. Use when the user invokes /list-prs or $list-prs, or asks for links to open pull requests created or updated during the session.
Skill Claude CodeCodex
List the repository web URLs for every repository changed during the entire current session. Use when the user invokes /list-repos or $list-repos, or asks for links to all repositories touched, modified, committed, pushed, or otherwise changed during the session.
Skill Claude CodeCodex
List and reconcile canonical rules across a bounded collection of local repositories. Use when the user asks which rules repositories have, where they occur, or whether a shared rule has conflicting language.
Skill Claude CodeCodex
List and reconcile canonical skills across a bounded collection of local repositories. Use when the user asks which skills repositories have, where they occur, or whether a shared skill has conflicting language.
Skill Claude CodeCodex
Edit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI.
Skill Claude CodeCodex
Present plans for explicit approval and implement approved plans without silently ignoring encountered issues. Use whenever an agent presents a plan, resumes after a plan timeout or missing response, or implements an approved plan with incidental fixes, mandatory code simplification, and independent delivery metadata…
Skill Claude CodeCodex
List canonical skills or propagate requested skills, rules, dependencies, and applicable repository-neutral agent guidance across the user's repository collection and matching existing user-level installations, bootstrapping Agent Sync when needed. Use when the user invokes /propagate-skill or $propagate-skill alone…
Skill Claude CodeCodex
Security audit of a codebase — web apps, APIs, services, CLI tools, libraries, daemons, and more. Use when asked to find security bugs, do a security review, audit for vulnerabilities, or pen-test the code. Focuses on exploitable issues with real impact, not theoretical concerns or industry-standard behavior.
Skill Claude CodeCodex
Audit installed agent skills across every visible scope, then autonomously benchmark, upgrade, retire, and install user-selected skills through isolated blind evaluations and a resumable local dashboard. Use when the user asks to inventory skill quality, compare a skill with model-only behavior, improve skills…
Skill Claude CodeCodex
Upsert .agents source-of-truth files and implement concrete issues raised with the requested guidance.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: