Agents for Codex

945 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

code-challenger

361

elmoritz/agents-skills-setup

Agent Codex

Devil's advocate against a ticket's implementation as built — run every round of the pick loop, not once. Attacks the code that now exists with evidence — hidden coupling it introduced, a cheaper route it should have taken, an irreversible or load-bearing step, or a route the plan got wrong. Read-only; returns a…

2 20d ago A 106 tokens

nfr-analyst

362

elmoritz/agents-skills-setup

Agent Codex

Derives a ticket's non-functional requirements while it is still being written — as measurable statements that each carry their own verification. Invoke in /ticket-new step 2 (alongside the research agents, before the step 2.5 grilling) and on /ticket-refine's resume path, so unresolved requirements become grilling…

2 20d ago A 96 tokens

builder

364

maiscafe/video_motion

Agent Codex

Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…

2 1mo ago A 0 tokens copy · 83% MIT

director

365

maiscafe/video_motion

Agent Codex

Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.

2 1mo ago A 0 tokens copy · 100% MIT

finalize

366

maiscafe/video_motion

Agent Codex

Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.

2 1mo ago A 0 tokens copy · 100% MIT

analyzer

367

adamhjk/mvtt

Agent Codex

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

2 2mo ago A 0 tokens

comparator

368

adamhjk/mvtt

Agent Codex

Compare two outputs WITHOUT knowing which skill produced them.

2 2mo ago A 0 tokens

grader

369

adamhjk/mvtt

Agent Codex

Evaluate expectations against an execution transcript and outputs.

2 2mo ago A 0 tokens

code-simplify

370

julien777z/code-review-action

Agent Codex

Code-simplify code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked via Task after a parent gathers diff and file contents. Uses the code-simplify skill as the complete rubric.

2 5d ago A 58 tokens original MIT

e2e-runner

371

KaelSensei/MagicAIBuilder

Agent Codex

Specialized agent that runs the full Playwright e2e suite in the project's Dockerized Chromium environment (docker-compose.e2e.yml) and reports pass/fail. Use before pushing to GitHub to guarantee e2e never regresses on main. Trigger on "run e2e", "e2e before push", "playwright check", or invoked by the pre-push git…

2 3d ago A 87 tokens original MIT

build-engineer

372

pinkpixel-dev/agentskills-mcp

Agent Codex

Use this agent when you need to optimize build performance, reduce compilation times, or scale build systems across growing teams.

2 20d ago A 27 tokens copy · 98% MIT

dependency-manager

373

pinkpixel-dev/agentskills-mcp

Agent Codex

Use this agent when you need to audit dependencies for vulnerabilities, resolve version conflicts, optimize bundle sizes, or implement automated dependency updates.

2 20d ago A 29 tokens copy · 98% MIT

pinkpixel-dev/agentskills-mcp

Agent Codex

Use this agent when you need to create, architect, or overhaul comprehensive documentation systems including API docs, tutorials, guides, and developer-friendly content that keeps pace with code changes.

2 20d ago A 39 tokens copy · 94% MIT

analyzer

375

ZenlixAI/hitl-mcp

Agent Codex

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

2 1mo ago A 0 tokens copy · 100% MIT

comparator

376

ZenlixAI/hitl-mcp

Agent Codex

Compare two outputs WITHOUT knowing which skill produced them.

2 1mo ago A 0 tokens copy · 100% MIT

grader

377

ZenlixAI/hitl-mcp

Agent Codex

Evaluate expectations against an execution transcript and outputs.

2 1mo ago A 0 tokens copy · 100% MIT

analyzer

378

GktuOktay/ai-skills

Agent Codex

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

2 +1 4d ago A 0 tokens copy · 100% MIT

comparator

379

GktuOktay/ai-skills

Agent Codex

Compare two outputs WITHOUT knowing which skill produced them.

2 +1 4d ago A 0 tokens copy · 100% MIT

grader

380

GktuOktay/ai-skills

Agent Codex

Evaluate expectations against an execution transcript and outputs.

2 +1 4d ago A 0 tokens copy · 100% MIT

nika-author

381

supernovae-st/nika-plugins

Agent Codex

Writes and repairs .nika.yaml workflows with the deterministic authoring protocol. Use when the user wants repeatable AI work turned into a workflow file, asks for a .nika.yaml, or a nika check must pass. Routes intent to a template, fills the SLOT markers, then loops nika check until rc=0. Its craft is WRITING …

2 yesterday A 96 tokens AGPL-3.0

nika-debugger

382

supernovae-st/nika-plugins

Agent Codex

Root-causes failed or paused Nika runs from their hash-chained traces. Use when nika run exited red, a run paused on a prompt and needs the exact resume line, a NIKA-XXXX runtime finding needs a cause, or a trace must be verified and explained. Evidence-first — reads .nika/traces via nika trace; its craft is the…

2 yesterday A 113 tokens AGPL-3.0

nika-migrator

383

supernovae-st/nika-plugins

Agent Codex

Ports an existing script, Makefile target, CI job or prompt chain to a checkable .nika.yaml workflow. Use when converting ad-hoc automation to nika, when a shell script wraps LLM/HTTP/file plumbing, or when a prompt chain in a doc should become a runnable, auditable file. Inventories side effects first, maps steps to…

2 yesterday A 91 tokens AGPL-3.0

cavecrew-builder

384

Shawn5cents/agentskin

Agent Codex

Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.

1 5d ago A 76 tokens