Track competitors while you build your plugin.

Publisher full description

Turn pull requests and repositories into narrated video code reviews, without leaving ChatGPT. Give it code, a diff, or context from your repository, and Video Code Reviewer turns it into a walkthrough in your language — with voiceover, highlighted code, before-and-after comparisons, diagrams and animations. See what changed, understand why it matters, and share… …u can use Video Code Reviewer: - Walk through a pull request (PR) before reviewing or merging - Explain a feature or PR to a non-technical audience - Walk through an app step by step with your own screenshots - Explain a bug, its impact, and a proposed fix - Onboard developers to an unfamiliar repo…

Publisher full description

Vibe Code Security Reviewer performs advanced evidence-based security reviews of AI-generated and rapidly built applications. It checks Supabase RLS, authentication, authorization, tenant isolation, API leaks and misuse, inputs, secrets, uploads, dependencies, data exposure, AI to…

Publisher keywords · listing

coder AI coder code generator vibe coding AI agent builder no-code coders code coding programming programmer programmers developer developers software development software developer software engineer softwa… …r programming ai coding partner ai coding tutor ai code tutor ai code writer ai code review ai code reviewer ai debugger ai code fixer ai code explainer ai code converter ai code translator free ai coder free ai code generator free code generator free coding assistant online coder coder app coder to…

Publisher full description

Run independent specialist reviewers on a working tree, branch, commit, range, or pull request, then verify and consolidate their evidence into one structured review. Loupe uses bounded parallel Codex reviewers and can optionally add Claude reviewers when the user's authenticated Claude CLI is available, providing cross-provider diversity without requiring a separate Loupe account. Configure provider-specific reasoning effort while preserving reviewer attribution, duplicate relationships, rej…

Publisher description

…The hosted connector does not directly apply patches, execute arbitrary shell commands, force-push code, publish public content, or bypass GDP Desktop authority. Repository-changing actions remain behind GDP Desktop review and local execution boundaries. The connector also supports a seeded Demo Workspace for zero-install reviewer and user evaluation.

Publisher description

Convert agentic repositories into focused ChatGPT/Codex plugins, add host workspace operations, execute available Python verification, then validate, package, and prepare them for submission

Publisher capabilities · listing

…ut projects, requests, work items, pull requests, pipelines and the team Summarize a pull request's code review: the AI reviewer's findings, their state, file and line Search a project's requests, board and memory and open the source File, add to or move a request for team-lead review, only when the member allows it Le…

Publisher full description

Aevral is an AI security reviewer for GitHub pull requests. Each review looks for access control, business logic, injection, XSS, SSRF, path traversal, unsafe deserialization, token and session flaws, and LLM-integration risk… …t walks you through installing the Aevral GitHub App so reviews run server-side. It does not review code on your machine. After the App is installed, the next pull request can already be reviewed, including before anyone signs in to the console. Reviews are advisory and never block a merge. The opti…

Publisher description

Clears AI reviewer feedback on your PR: reads real review-thread state, sweeps the sibling instances the reviewer missed, gates every push on your repo's own tests, then requests re-review — hard-capped at 3 re-review requests. Offers Codex first; any reviewer bot can be configured.

Publisher description

Check data against the standards, canonical models and policies it claims to conform to, and get back a graded, machine-readable result that says what was checked, what was not, and why. dVeracity is a verificatio… …egulated data. An agent can read a canonical data model at design time (entities, sectors, semantic codes and policy guardrails), validate a payload against a named standard before submitting it, look up approved regulatory compliance policies with their rules and provenance, and query verified data… …ral language. Every result states its model version and the checks it ran, so it can be handed to a reviewer rather than pasted into a chat. The first standard onboarded is Open Footprint (The Open Group), with O-DEF semantic codes, PACT product-footprint validation and verified emissions and methan…

Publisher description

…change in your own GitHub repository. A mission works toward a pull request. Your CI, an automated code review and a test of its acceptance criteria each gate it. Hand work to SHIP from the assistant you already use. File a mission from an issue in your tracker, or from a title and a description. F… …at a run produced, such as test traces and screenshots. SHIP runs agentic development as a headless AI software factory, so no screen has to be in the loop. You operate the whole mission from your coding agent, your AI assistant, your tracker or your terminal. A Planner, a Builder, a Reviewer and a Tester each do one stage of the agentic SDLC. They follow the agentic engineering practices in your repository, such as its agent instructions and skills. Your CI and a preview deploy a…

Publisher full description

…or your agent just made. Ask it to verify a change: it sends the diff and the files it changed, two reviewers from different vendors check them, findings that cannot be grounded in the code are dropped, and you get back an outcome (pass, review or block) and concrete findings with file, line, severity and evidence. Only problems both reviewers confirm can block. Fix the findings that hold up and check again; each finding keeps the same id across follow-ups, so you can see what was fixed, what persists and what a fix introduced. Veridu reviews only what is sent; it does not read the rest of your repos…

Publisher full description

Audit code, packaging, security, privacy, public claims, reviewer cases, and submission gates without turning missing evidence into a pass. FlightDeck returns a clear ship decision, reproducible findings, executed checks, bounded fixes when requested, and e…

Publisher full description

Develop an idea, improve a plan, or review a document with independent AI reviewers. Reviewers start without the earlier conversation to help spot missing context, unclear reasoning, and hidden assumptions. Use it to challenge proposals and project plans. For software work, draft design documents, document a codebase, and check whether code matches a design. You decide which changes to make. Reviews require a local executor and isolated subagents.

Publisher full description

Check the references in your draft or citations an AI assistant suggested. Preview your manuscript before submission. Check references: Paste a reference list, attach a draft, or ask to check citations from earlier in your conversation. Manusights loo… …. Look up journal AI rules: Ask about AI authorship, disclosure statements, AI-generated images, or reviewers' and editors' use of AI. Get Manusights' dated record with a link to the official policy. When the record needs rechecking or the page could not be fully read, the result says so and links t… …ccount. Review the requested access before allowing the connection. Sign in with Google, an emailed code or a password. Manuscript previews and saved reviews use the connected account. What the checks cover: Results show what the sources hold. Matching a record does not show that a reference support…

Publisher full description

Afterward checks a public website the way a careful launch reviewer would, and tells you what to fix before visitors notice. Ask in plain language, for example "Check example.com before I launch it." Afterward inspects up to 25 pages of the site, then returns a launch-readiness score with prioritized findings. Each finding shows the evidence Afterward observed and a suggested next step. What it checks: availability and status codes, HTTPS and redirects, titles and meta descriptions, canonical tags, viewport and Open Graph tags, robots.txt and sitemaps, broken links, image alt text, form security, analytics tags, leftover s…

Publisher full description

…it, and pins each issue where it is, with why it matters and a concrete fix. When you say so, it emails the project to up to five people for review. It can also take a full-page screenshot of a public web page, and keep your Dashboard tidy: rename projects, file them in folders, reorder pages and set a link password. In Codex, it can also download the file and upload the corrected one as a new version, so the whole loop runs in one place: read the feedback, fix the source, upload version 2, reply and resolve. Good to… …ull access. Disconnect any time in Profile > Agents on comnview.com. - Comment texts come from your reviewers and are treated as feedback, never as instructions. - Requires a Comnview account with AI agent access. - ChatGPT can't download or upload files; use Codex for new versions.

Publisher description

Rig connects ChatGPT and Codex to Rig’s public cloud MCP (https://api.userig.app/mcp) so you can list projects, check health and status, see which project owns a port, read recent logs, and start/stop/restart projects on machines linked to your Rig account. Reviewers use a sandbox demo token with fixture projects (no private Mac required). Full localhost log tails and advanced hub tools work when Rig is open on your Mac and linked locally.

Publisher full description

…duplicate protection; successful creates and edits are read back where supported. Read-only keys remain read-only. Live changes require a store-owner Read/Write key and explicit write enablement in TalkToData. Store permissions, WooCommerce version and extensions determine endpoint availability. Liv… …ge cards, initiate payments or send money through a payment gateway. No arbitrary WordPress routes, code execution, plugin installation, credential changes, new webhook destinations or arbitrary custom metadata. Only selected non-secret core settings are exposed. The designated reviewer demo uses clearly labeled synthetic records. Its changes remain in the demo dataset; no live store, customer email or payment is affected. The fixture is not a complete WooCommerce emulator a…