MARKET RESEARCH

CodexPluginStats: Codex plugin directory

Codex Plugin Stats: discover plugins, explore their skills and track catalog growth and observed changes.

Explore 5,295 plugins across 14 categories.

Selected:evaluation ×

All plugins 43

1–36 of 43

All query words must match. Use quotes for an exact phrase. Matches include publisher text, keywords and attributed research.

Discover Codex plugins by task and category
Plugin / developerCategoryFollow
CRIADOR / ReefRONALD FERRARI SOARESGuidance and references for building continual self-improvement workflows for agents with Reef.

Publisher capabilities · listing

Agent evaluation Self-improvement workflow design

Show in context →
2 more matching sources

Publisher keywords · listing

agents continual-learning self-improvement reef harness evaluation

Show in context →

Publisher full description

Guides structured evaluation, reflection, and iteration for improving agent behavior, prompts, workflows, and reliability.

Show in context →
Developer ToolsVersion 1.0.0
View details →
EvalDossierMiguel HerreroOffline verification and fixed synthetic conformance for portable signed EvalDossier dossiers.

Publisher capabilities · listing

Check signed evaluation dossier integrity offline Report the declared evidentiary basis of a verified dossier Run the fixed synthetic conformance workflow

Show in context →
2 more matching sources

Publisher keywords · listing

ai-agents evaluation attestations offline-verification

Show in context →

Publisher full description

EvalDossier checks incoming signed evaluation dossiers locally before you rely on them. It checks schema conformance, integrity, signatures, and caller-supplied audience and nonce pins, then reports the result’s declared evidentiary ba…

Show in context →
Developer ToolsVersion 0.2.1
View details →
LLM & Agent Builder CopilotKrishna SathvikDesign reliable LLM, tool, MCP, and agent workflows.

Publisher capabilities · listing

…d guardrails, human approvals, least-privilege controls, and prompt-injection defenses Create agent evaluations for task success, tool use, trajectories, side effects, latency, and cost Design tracing and observability for model calls, tools, handoffs, approvals, retries, and outcomes Use current of…

Show in context →
Developer ToolsVersion 0.1.0
View details →
Matt Skills CuratedMamdouh AboammarCurated engineering, AI/ML, and agentic productivity Skills adapted for ChatGPT and Codex.

Publisher capabilities · listing

…ry-source technical research AI & ML model engineering Self-healing data remediation ML statistical evaluation & metrics Cognitive workspace reasoning (J-space) Autonomous goal contracts Skill conductor authoring & evals Git safety guardrails & pre-commit Workflow design & session handoffs Course sc…

Show in context →
Developer ToolsVersion 1.1.0
View details →
Codex ReplayOpenAIRun independent Codex replays in the in-app browser or your system browser.

Publisher keywords · listing

codex replay evaluation

Show in context →
1 more matching sources

Publisher full description

…ected by default. Multiple replay sessions can run in parallel. Selection, execution, verification, evaluation, and results stay in the browser controller instead of a guided chat workflow.

Show in context →
ProductivityVersion 1.0.128
View details →
CompText BenchmarkCompText LabsRun, inspect, and compare reproducible Raw vs CompText benchmarks with quality-first evidence.

Publisher keywords · listing

benchmark context-compression evaluation comptext

Show in context →
Developer ToolsVersion 0.1.5
View details →
MI.LO Prompt OptimiserMichael LockettMI.LO improves and designs prompts for AI models, agents and workflows.

Publisher keywords · listing

prompt engineering prompt optimisation agents evaluation

Show in context →
1 more matching sources

Publisher full description

…repeated workflows. It preserves user requirements, checks tool and permission boundaries and adds evaluation guidance when it matters.

Show in context →
ProductivityVersion 0.1.0
View details →
Plugin EvalOpenAIEvaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and g...

Publisher keywords · package

codex plugin skill evaluation quality budget

Show in context →
Developer ToolsVersion 0.1.2
View details →
RAG & GenAI CopilotKrishna SathvikProduction-focused RAG architecture, debugging, evaluation, security, and reliability.

Publisher keywords · listing

rag genai retrieval llm evaluation security observability

Show in context →
2 more matching sources

Publisher description

Production-focused RAG architecture, debugging, evaluation, security, and reliability.

Show in context →

Publisher full description

…ng, indexing, retrieval, reranking, context construction, generation, citations, authorization, and evaluation; design practical RAG architectures; build retrieval and groundedness evals; review prompt-injection and data-leakage risks; and improve observability, latency, and cost. It favors measurab…

Show in context →
Developer ToolsVersion 0.1.0
View details →
RAGOpsDUC THANG LUUOffline, explainable release gates and evidence bundles for RAG systems and AI agents.

Publisher keywords · listing

rag ai-agents evaluation release-gates regression-testing

Show in context →
ProductivityVersion 2.0.2
View details →
100Hires ATS100Hires Inc.

Publisher description

Recruiters use 100Hires to track jobs, candidates, applications, interviews, and evaluations. This connector lets ChatGPT read your real ATS data and act on it — move candidates between stages, schedule interviews, send templated rejection or outreach messages, log evaluations, an…

Show in context →
Business & OperationsVersion 2.0.0
View details →
AdAnalyzePyxl

Publisher description

…keting and advertising content. It analyzes ads, landing pages, and marketing copy using predefined evaluation frameworks and highlights clarity issues, missing elements, and potential risks.

Show in context →
Business & OperationsVersion 1.0.0
View details →
Argovance Skill OSSTEFFEN CLAUS

Publisher full description

…epresentation-first creative production, accessibility and interface-language review, behavioral AI evaluation, task and context control, evidence validation, independent review, software delivery, high-fidelity interfaces, realtime 3D, defect repair, code migration, performance, regression testing,…

Show in context →
ProductivityVersion 1.1.0
View details →
Autocalls AIMULTICODE S.R.L.

Publisher description

…like. Then close the loop — list your calls, open any one to read its full transcript and post-call evaluation, and update the assistant or its tools to fix what went wrong, all in the same conversation. Manage the rest of your account too: knowledgebases and documents, phone numbers and SIP trunks,…

Show in context →
ProductivityVersion 1.1.0
View details →
Brainbase MCPBrainbase Labs

Publisher description

…T and Codex. It supports revision-safe agent changes, registry skills and MCP server configuration, evaluations, orchestrations, schedules, and task runs, with explicit confirmation for destructive actions and OAuth-based access to the user's Brainbase workspace.

Show in context →
Developer ToolsVersion 1.0.0
View details →
Chess by Max HealthMax Health Inc.

Publisher description

…ove and main line, and key positions can be illustrated on a board with the recommended move and an evaluation bar.

Show in context →
EntertainmentVersion 2.0.0
View details →
Cloud & Hosting AdvisorRavi K Gupta

Publisher description

…ture, VPS providers, WordPress hosting, and managed servers. Delivers authentic, unbiased technical evaluations of compute performance, bandwidth, uptime, and pricing with direct access to verified hosting services.

Show in context →
ProductivityVersion 0.1.0
View details →
CovalCoval

Publisher description

Coval helps teams inspect AI agents, test sets, personas, metrics, and evaluation runs; create and refine evaluation resources; launch evaluations; and ask Sofia for read-only analysis grounded in their Coval organization.

Show in context →
Developer ToolsVersion 2.0.0
View details →
CryotosPiqoTech Software Solutions Private Limited

Publisher description

MCP for the Maintenance team to connect to the Cryotos CMMS application and fetch key details for evaluation.

Show in context →
Business & OperationsVersion 1.0.0
View details →
Cryptography Research SkillsZiyang Jin

Publisher full description

…For implementation work, use separate workflows for protocol correspondence, benchmark accounting, evaluation writing, and reproducible artifacts. The skills emphasize precise models, evidence provenance, conservative claims, and keeping the requested scope small. Proof audits distinguish confirmed…

Show in context →
Education & ResearchVersion 0.1.0
View details →
DecionisBinaries

Publisher description

…ied approval through Presence and re-evaluate the action using the resulting signed evidence. Every evaluation produces a verifiable Decision Dossier and cryptographic evidence for audit and accountability. Use Decionis to govern agent-initiated payments, refunds, commerce operations, enterprise wor…

Show in context →
SecurityVersion 1.0.1
View details →
Find Your GreatFind Your Great

Publisher description

…ioral patterns from your activity. Ask things like: - "What did I work on this week?" - "How are my evaluation scores trending?" - "Draft an impact update for my manager covering the last two weeks" - "What decisions did I make on the authentication project?" The connection is OAuth-secured with gra…

Show in context →
ProductivityVersion 2.0.0
View details →
FormbyteVidline Inc.

Publisher description

…er feedback. · Design a fillable application form for job applicants. · Formbyte, generate a course-evaluation survey for my online class. One prompt gives you a polished form plus live Q&A analytics, all in chat. Connect Formbyte and type “create a form” to turn questions into decisions.

Show in context →
ProductivityVersion 1.0.0
View details →
get-fableMamdouh Abo Ammar

Publisher description

…search, planning, test-first changes, delegation, verification, review, security, release, handoff, evaluation, and recovery across 25 canonical skills.

Show in context →
Developer ToolsVersion 1.5.1
View details →
Git Diff Patcher BridgeMuhammet Avcı

Publisher description

…boundaries. The connector also supports a seeded Demo Workspace for zero-install reviewer and user evaluation.

Show in context →
Developer ToolsVersion 2.0.0
View details →
GossetGosset

Publisher description

…ission longer research reports such as competitive landscapes, standard-of-care summaries and asset evaluations, which you can list and fetch later. Gosset is an industry research tool, not a source of medical advice.

Show in context →
Business & OperationsVersion 1.0.1
View details →
Intuitive Software DesignArcanEdge LLC

Publisher full description

…s focused guidance, formal audits, smallest-complete-change improvements, and an 11-case behavioral evaluation kit.

Show in context →
Developer ToolsVersion 1.3.1
View details →
JotformJotform Inc.

Publisher description

…ete form that you can refine through conversation. Build request forms, application forms, surveys, evaluation forms, report forms, consent and acknowledgement forms, lead generation forms, feedback forms, quizzes, registration forms, RSVP forms, order forms, appointment booking forms, and more. Add…

Show in context →
ProductivityVersion 6.2.1
View details →
LuneTony

Publisher description

…tion links, and full text when available. It also provides curated guidance for literature reviews, evaluation design, ablation studies, and venue selection. From early ideas to publication-ready research, Lune helps researchers and technical teams move faster with traceable sources, deeper literatu…

Show in context →
Education & ResearchVersion 1.0.0
View details →
Model CompassNEEKHIL VATSA

Publisher full description

…e instead of intuition. It joins the live Codex catalog with official OpenAI pricing, guidance, and evaluations, clearly labels domain-specific proxies and unknowns, and offers opt-in interactive comparisons or controlled trials on your own task. Visuals stay quiet until you ask for them.

Show in context →
ProductivityVersion 0.2.0
View details →
OpenlayerOpenlayer

Publisher description

Openlayer helps teams inspect AI projects, data sources, traces, tests, evaluation results, and governance controls, and manage private workspace resources through ChatGPT.

Show in context →
Developer ToolsVersion 1.0.0
View details →
PartnerProf - Quanntum CorePETR SCHOEN

Publisher description

…he admitted state remains deterministic, reproducible, and fully auditable. PartnerProf enables the evaluation of quantum and high-dimensional state-space problems that would otherwise be computationally impractical, including classes of simulations that may remain intractable even for current quant…

Show in context →
Scientific ResearchVersion 2.0.4
View details →
Partnership Leaders ResearchPartnership Leaders

Publisher description

…arch answers, evidence lookup, company and taxonomy scans, event summaries, and rubric-based answer evaluation for testing.

Show in context →
Business & OperationsVersion 2.0.1
View details →
Prompt EngineerThe Doers Firm LTD

Publisher full description

…clear, model-aware prompts; improve existing prompts while preserving intent; and design practical evaluation cases to compare quality, reliability, and safety. Distinguish prompt-only behavior from capabilities that require tools or application code. Treat prompt results as empirical, model-depend…

Show in context →
Developer ToolsVersion 0.1.0
View details →
Rohas Legal AI: MediationRohas Nagpal

Publisher description

…rategy, mediation brief and opening, outcome documentation, party-interest analysis, and settlement evaluation skills.

Show in context →
1 more matching sources

Publisher full description

…ediation briefs, opening statements, outcome documentation, party-interest analysis, and settlement evaluation against the litigation alternative.

Show in context →
ProductivityVersion 0.2.1
View details →
Scholar ResearchSyed Fasih Haider Raza Rizvi

Publisher description

…. Topic ideas, research questions and hypotheses, theoretical frameworks, search strategies, source evaluation, paper breakdowns and Q&A, literature reviews, evidence synthesis, research gaps, systematic reviews, annotated bibliographies, citations in APA, MLA, Chicago, Harvard, IEEE and more, refer…

Show in context →
Business & OperationsVersion 1.1.0
View details →