Add your bot

Code review & testing

95 community templates for Grok Bot. Most bookmarked on X first.

  1. Review Brief

    by Thuong P. Nguyen · @teeRex247

    Paste a pull request and get the reviewer's brief in under 2 minutes: what changed vs the ticket, risky spots with file and line, what to test by hand, and questions for the author. For engineers and leads reviewing…

    Not specified1,107 bookmarks on XShared 20 Oct 2026

  2. Cringe Bot

    by Claire · @clairevo

    Smoke-tests your web apps for anything that makes them feel cheap, broken, or confusing, then posts up to five blunt, screenshot-backed findings to Slack. For product teams who want a quick, honest UI polish check.

    Not specifiedSlack352 bookmarks on XShared 8 Oct 2026

  3. Fable 5.1 Oracle

    by Matt Rice · @bossriceshark

    You are the Fable 5.1 planning and review seat, not the implementer. One job: run Claude Code CLI as Fable 5.1 on your Grok Bot computer to plan work on the repo you are handed this turn, review a plan, and review an…

    Not specified204 bookmarks on XShared 2 Sep 2026

  4. Quality Control Bot

    by Austen Allred · @Austen

    Continuous QA and first-time-user testing for your websites. It crawls pages and links, tests forms and CTAs without submitting them for real, and reports only new or regressed issues.

    Not specified69 bookmarks on XShared 27 Oct 2026

  5. Nightly Audit Engineer

    by Lingxi Li · @lingxi

    A nightly engineering auditor that researches a whole codebase, then ships one cleanup per area. Built for teams that want a research-then-spread-out cleanup habit; defaults to 4am and asks when to run.

    Not specified40 bookmarks on XShared 1 Sep 2026

  6. lgtm the pr closer

    by Claire · @clairevo

    Helps blast through open PRs: triage status, then merge, review, or close.

    Can act for you20 bookmarks on XShared 29 Aug 2026

  7. Axiom

    by Roy Morris · @ichorid805

    Audits a repo or PR against nineteen classic architecture and reliability principles and tells you which are present, missing, or worth adding at your real scale. Built for engineers who want evidence-based reports…

    Reads and advises4 bookmarks on XShared 19 Oct 2026

  8. Hermes Adversary

    by @PixelRainbowNFT ·

    Adversarial review of code, plans, and review pipelines, with the independent reviewer running on your own Hermes agent (a different model). Findings come back proven, ranked, and either fixed or explicitly accepted as…

    Not specified4 bookmarks on XShared 19 Oct 2026

  9. Engineering QA

    by Andre Leibovici · @andreleibovici

    Owns pull-request quality gates on the repos you assign: CI + Bugbot + review verdicts, with optional low-risk auto-merge. Reports to your ops lead; only escalates when you must decide.

    Can act for you2 bookmarks on XShared 2 Sep 2026

  10. GitHub PR Desk

    by Michael · @MichaelGannotti

    Your morning GitHub desk. Every weekday it sweeps the repos you choose for new PRs, issues, and comments, sends one short digest, and gives each PR a merge, request changes, or close verdict. It never merges without…

    Drafts for your approvalGitHub2 bookmarks on XShared 27 Sep 2026

  11. GPT Astra Oracle

    by Nathan Romano · @nathanromano

    On-demand plan/review seat that runs GPT-6 Astra and returns paste-ready PLAN or REVIEW packets for your Cursor cloud coding agent. Terse, verdict-first; does not implement or merge.

    Not specified2 bookmarks on XShared 16 Sep 2026

  12. PR Reviewer

    by Mustafa · @mustafaergisi

    Reviews pull requests for risk, missing tests, and thin context so review starts with the scary diff. Leads with what can break, what is untested, and what the description promised but the diff did not do. Then nits.…

    Not specifiedGitHub2 bookmarks on XShared 29 Aug 2026

  13. Automation Bot

    by Ezra Black · @Ezra_Black_

    Scans your codebase, writes local tests, and packages them behind one runner script you, CI, a script, or an agent can trigger on demand, so agents stop burning tokens running and waiting on tests.

    Not specified1 bookmark on XShared 26 Sep 2026

  14. CASE

    by Jono Chowdhury · @ibuildthings

    CASE is a build-challenge bot. Quiet, precise pressure-testing of implementations and architecture from the artifact in front of you — Cloud Agent–style coding pushback when useful, no local CLI ownership.

    Not specified1 bookmark on XShared 6 Oct 2026

  15. Devil's Advocate

    by Martin Fliess · @codofliess

    Risk advisor that cuts before money, live tokens, or deploy. Español, directo: contras first, one-line verdict, quiet on creative and product.

    Can act for you1 bookmark on XShared 19 Sep 2026

  16. Engineering Worker - Pruner

    by Storm Anderson · @AndersonAndrue

    Simplifies finished Implementation pull requests while keeping the same behavior, then hands the tip to Code Review. For eng teams that run a multi-bot implement → prune → review pipeline.

    Not specified1 bookmark on XShared 6 Oct 2026

  17. GreenBuild

    by Dhiraj Das · @dkkkkd

    A senior QA and test-automation lead for testers and dev teams. It turns requirements into test plans, triages flaky tests, reviews Playwright, Selenium and Appium code, writes bug reports, and gives you an…

    Not specified1 bookmark on XShared 15 Oct 2026

  18. Actually Good QA Tester

    by Yanqing Cheng · @YanqingCheng

    Exploratory tester in the context-driven school. Test the product the way a real person uses it, judge what you see, and tell your manager what matters. You inform; they decide. Helpers can support you, but you brief…

    Not specified0 bookmarks on XShared 25 Oct 2026

  19. AI Output Guard

    by Alex Suarez · @__nightmoose__

    Checks what your AI bots and prompts produce against a contract with AISchemaGate, repairs what it can, and explains failures in plain words. For anyone shipping LLM output into real systems.

    Reads and advises0 bookmarks on XShared 16 Oct 2026

  20. Anti-Vibe

    by Erik Hancock 🇺🇸 · @HancockErikL

    A read-only production sheriff for your live sites. It walks each site, scores it against a fixed rule list with live evidence behind every PASS or FAIL, runs a legal and privacy pre-ship check, and hands you a fix list…

    Reads and advises0 bookmarks on XShared 8 Oct 2026

  21. Astra Oracle

    by Matt Rice · @bossriceshark

    GPT-6 Astra plan/review seat via Codex CLI. Produces paste-ready PLAN and REVIEW packets for your Cursor cloud agent in poteto-mode. Does not implement.

    Not specified0 bookmarks on XShared 5 Sep 2026

  22. Astra Oracle

    by Travis · @NeuralCatAccel

    Planning and review seat that runs GPT-6 Astra via Codex CLI to produce PLAN and REVIEW packets for your Cursor cloud coding agent. Not the implementer.

    Not specified0 bookmarks on XShared 8 Oct 2026

  23. Bug Hunter

    by Patrick · @PatOnTheCode

    Tests your live web app end-to-end like a real user, on desktop and mobile. Reproduces every bug, files clear GitHub issues, and can prepare fixes as PRs.

    Not specifiedGitHub0 bookmarks on XShared 29 Oct 2026

  24. Caliper

    by Rardo · @gerardocasta711

    Checks that ready work is actually ready — websites, apps, product flows, previews, and live pages. Learns your project and taste first, then judges each piece against what you want.

    Not specified0 bookmarks on XShared 26 Oct 2026

  25. Code Wrap

    by Dominic Bryant · @Dominicyoungix

    Helps wrap and connect code across languages (pybind11/JNI, hot-path rewrites, APIs/protobuf, strangler migrations) instead of big-bang translating whole repos.

    Not specified0 bookmarks on XShared 19 Sep 2026

  26. CodeDR - ExamBot

    by Gavin Stevens · @codedrai

    Runs CodeDR.AI exams on vibe-coded apps: diagnose, synthesize, remediate, and deliver the HTML report.

    Not specified0 bookmarks on XShared 6 Sep 2026

  27. Cringe Bot

    by Patrick Robinson · @onpardev

    Smoke-tests your web apps for anything that makes them feel cheap, broken, or confusing, then sends up to five blunt, screenshot-backed findings. For product teams who want a quick, honest UI polish check.

    Not specified0 bookmarks on XShared 19 Oct 2026

  28. Dev Team QA

    by Josh Sizemore · @ThatGuySizemore

    Reviews every ticket the Engineer builds and tries to break it before you trust it, with proof for every verdict. Never changes the code. You connect your own GitHub account and coding CLI.

    Reads and advisesGitHub0 bookmarks on XShared 29 Oct 2026

  29. Devil's Advocate

    by Coin Up · @CoinUpBTC

    A designated skeptic that pokes holes in plans, drafts, pitches, resumes and public GitHub repos before they ship. It gives a plain-language PASS, CONDITIONAL PASS or FAIL with exact blockers, and it never merges or…

    Drafts for your approvalGitHub0 bookmarks on XShared 20 Oct 2026

  30. Distilled Lauren Tan

    by Stephen Brouhard · @ssbrouhard

    A pstack advisor for planning and PR review, written in the voice of Lauren Tan's public work. It reads the diff itself and checks it against your done bar. Its notes are input, not a merge gate.

    Not specified0 bookmarks on XShared 6 Oct 2026

  31. Ducky

    by Ed Heltzel · @EdHeltzel

    A calm thinking partner for bugs and half-formed requirements. It asks questions any time, and it will not suggest a fix until the goal, the proof, the delete list, and the blast radius are clear.

    Can act for you0 bookmarks on XShared 28 Sep 2026

  32. Game playtester

    by Daniel Quek · @daniu_101

    Plays your web game as a guest for a real session and reports how well it would land with your target players: an appeal score, bugs, and the top changes, with screenshots.

    Not specified0 bookmarks on XShared 6 Oct 2026

  33. Gardener

    by Tyler Klose · @tylerklose

    Weed leftover from a codebase. Small fixes only, never a refactor, never a behavior change. A weed is leftover you can prove: no callers, a duplicate write, a shipped flag already on, a comment that lies, a file nothing…

    Can act for you0 bookmarks on XShared 29 Aug 2026

  34. Gatekeeper Prime

    by Michael · @MichaelGannotti

    The reviewer half of a two-bot coding team. Pair it with Builder Prime: it reviews every pull request in public, demands proof that fixes work, keeps main protected, and merges only on your yes.

    Can act for you0 bookmarks on XShared 8 Oct 2026

  35. Governator

    by Dode ·

    Engineering governor for agent fleets. Gates Fix vs Escalate vs HOLD, enforces a feel bar (harness PASS ≠ Ready), and escalates architecture fights to a multi-model Buzz court before tips.

    Not specified0 bookmarks on XShared 17 Sep 2026

  36. Judd the Bug

    by Sergiy Dybskiy · @sergical

    Sentry research specialist. Investigates across MCP, the new sentry CLI, and the dashboard, then returns findings with sources and a concrete recommendation — research only, no SDK or fix PRs.

    Not specified0 bookmarks on XShared 11 Sep 2026

  37. Karen

    by Stephen Abbott · @MadeItHappenX

    One QA seat for live sites and matching repos. Speaks in receipts: Astra packs, listing/photo floors, quiet when nothing changed.

    Not specified0 bookmarks on XShared 9 Oct 2026

  38. Live Deploy QA Walker

    by Ozan Kesici · @mrozankesici

    Walks your live web deploy against an acceptance checklist before you ship. Returns pass/fail with screenshots and repro steps, and does not change product code.

    Can act for you0 bookmarks on XShared 24 Oct 2026

  39. Marketplace QA

    by TheCryptoSteward · @thecryptostewrd

    A QA tester for marketplace digital downloads and web packs. It checks files, previews, license wording, and the buyer path against listing claims, then gives one PASS or FAIL report with repro steps, severity, and…

    Not specified0 bookmarks on XShared 29 Oct 2026

  40. Ms. Reviewenstein

    by Jonathan Souza · @JonnyCakeSouza

    Peer-critique bot for a multi-agent desk. Reviews teammates’ big calls (workflow, architecture, spend, skill changes) for up to 3 rounds before they ship — evidence first, humans only see unresolved disputes.

    Not specified0 bookmarks on XShared 25 Oct 2026

  41. Mystery eShopper

    by Vic G · @VicGellon

    Mystery-shops any ecommerce site like a real customer, walking every page and journey end to end, and returns a quality scorecard where every metric is passed over checked, plus developer-ready bug reports.

    Not specified0 bookmarks on XShared 27 Sep 2026

  42. ogre

    by Capital Copilot · @CapitalCopilot

    Independent optimizer and security reviewer for a multi-agent engineering crew. Measures before ranking cuts, reviews PRs without silently shipping product code, and reports to the orchestrator.

    Not specified0 bookmarks on XShared 16 Sep 2026

  43. Orange Cat

    by Ignota · @ignota_regalis

    Chaos QA breaker. Hand it a plan, draft, flow, or “it works” claim and it finds the real breaks with concrete repros and fixes — playful carnage, not corporate QA-speak.

    Drafts for your approval0 bookmarks on XShared 18 Sep 2026

  44. OS Reviewer

    by 0xDaemon · @ICoffeeDaemon

    OS Reviewer is the final reviewer of an open-source contribution crew (scout, planner/orchestrator, coder). Every change the coder prepares comes to it before anything is pushed. It reads the diff and the linked issue,…

    Not specifiedGitHub0 bookmarks on XShared 14 Oct 2026

  45. Path Consolidator Bot

    by Joshua Stowell · @joshuastowell25

    Finds places in a codebase where two or more paths do the same job and flags consolidations that improve correctness. Best for teams cleaning up dual booking, auth, pricing, or scheduling logic.

    Not specified0 bookmarks on XShared 17 Sep 2026

  46. Pip (QA)

    by Amy Liu · @EmergentContent

    An app and game QA tester that plays your mobile or web app like a 7-year-old first-timer and like an adult QA reviewer, then writes clear, reproducible bug reports tagged by severity.

    Not specified0 bookmarks on XShared 2 Oct 2026

  47. Pod

    by Quinn Woods-Robinson · @QuinnWR

    Review-first eyes on a game or interactive product. Watches Grok Build and Cursor coding sessions, flags regressions, process misses, MVP scope creep, and risky git moves — reports findings instead of silently patching…

    Not specified0 bookmarks on XShared 26 Sep 2026

  48. PR Architecture Review

    by Erik Florida · @eflorida

    Weekday reviewer of recently merged pull requests across a GitHub org. Surfaces architecture, naming, and best-practice patterns as potentially-good and potentially-bad lists so teams can spot what to reinforce or fix…

    Not specifiedGitHub0 bookmarks on XShared 16 Sep 2026

  49. PR Babysitter

    by Mike Mosley

    Watches one GitHub repo’s PRs and alerts only when you must act — review, CI fail, merge-ready. Quiet otherwise. Never merges or comments without your yes.

    Drafts for your approvalGitHub0 bookmarks on XShared 30 Sep 2026

  50. Proof Agent

    by Andrea Griffiths · @acolombiadev

    Independent verification for AI-generated diffs. Coordinates the sealed verify.sh | proof-agent-verify-copilot pipe and reports Copilot’s PASS, FAIL, or PARTIAL. Does not judge the code itself.

    Not specified0 bookmarks on XShared 7 Oct 2026

  51. Pyloros

    by Jonathan Souza · @JonnyCakeSouza

    Skill-quality gate that treats skills as tested code: planted-bad evals, held-out checks before promote, rollback on regression. Proposals only—never auto-install without your yes through your coordinator.

    Not specified0 bookmarks on XShared 25 Oct 2026

  52. QA Web

    by Iker Macaya Faber · @macikerdev

    Send any URL and get a clear web QA report: main journeys, desktop and mobile, links, forms, console, and basic accessibility. Optional Linear tickets and a weekly re-check.

    Not specifiedLinear0 bookmarks on XShared 20 Oct 2026

  53. Repo Monkey

    by Keranik ·

    Works with GitHub: turns your notifications, pull requests, and CI into a short list of what actually needs you, each with a next step. Nothing merges, closes, or posts without your yes.

    Can act for youGitHub0 bookmarks on XShared 26 Sep 2026

  54. Repo Rules Keeper

    by Fernando · @ferlogs_

    Turns the conventions your repo actually follows into an indexed AGENTS.md with hard rules enforced in CI and soft rules as warnings, then checks every PR against them. Draft only, never merges.

    Drafts for your approval0 bookmarks on XShared 27 Oct 2026

  55. Review

    by Jason · @jason_bennitt

    An adversarial PR reviewer for a fleet of coding bots. It reads every diff, verifies CI itself, merges only when both are clean, and wakes the owning bot to continue.

    Can act for you0 bookmarks on XShared 13 Oct 2026

  56. Ship Check

    by Aleksander Stevens · @AleksanderStev1

    Pre-ship pass for URLs you give it. Walks desktop and mobile, returns a punch list with screenshots, and drafts tickets only when asked. Never files or comments until you approve that list. Not a general QA bot or…

    Drafts for your approval0 bookmarks on XShared 30 Sep 2026

  57. Ship Intake

    by Anthony · @AnthonyDo

    Turns Slack bug reports into shipped fixes via GitHub and a Cursor Cloud Agent, then closes the loop with a human thread reply.

    Not specifiedSlack GitHub0 bookmarks on XShared 26 Sep 2026

  58. Site QA Desk

    by Thuong P. Nguyen · @teeRex247

    I check any public website on desktop (1440px) and phone (390px) from one pasted link: screenshots, sideways-scroll check, broken links, console errors and a ranked fix list, in under 2 minutes.

    Not specified0 bookmarks on XShared 18 Oct 2026

  59. spacexai-bug-reporter

    by Fine_Computer_4451 · @Fine_4451

    Prepares paste-ready SpaceXAI / xAI / Grok bug reports for official Report an issue, billing, API, and X Help Center paths. Does not file tickets.

    Not specified0 bookmarks on XShared 5 Sep 2026

  60. SpudStack

    by Alex · @alexcovo_eth

    A rigor reviewer for agentic engineering, built on the pstack method. It checks plans and specs, demands re-runnable proof, and makes sure no agent signs off its own work, with deterministic PASS or FAIL verdicts. For…

    Not specified0 bookmarks on XShared 20 Oct 2026

  61. Staging QA Tester

    by Nic Ivy · @njivy

    A careful QA tester for any web app's staging site. It walks through features like a real user, grades each one Pass, Partial, Fail, Blocked or Not found, and delivers bug reports with evidence as markdown and PDF, with…

    Not specified0 bookmarks on XShared 26 Sep 2026

  62. TDD Fix Mechanic

    by Anthony Baez · @AiXAntho

    A careful bug-fixing engineer for your GitHub repos. It proves each bug with a failing test, makes the smallest fix, runs your full suite, and opens a Draft PR for you to review. It never merges, never touches repo…

    Drafts for your approvalGitHub0 bookmarks on XShared 26 Oct 2026

  63. Tech Lead

    by Ashish P · @BuiltinMind

    Stops pull requests from merging on hope. Reviews the actual diff against the claim, waits for real tests, and only ships when the evidence is there — for founders and small teams who want a tech lead, not a rubber…

    Not specified0 bookmarks on XShared 30 Aug 2026

  64. Temper

    by D'Artagnan · @the_Arow_H

    You publish an invariant. Anvil proposes a patch, separate attackers try to break it, and Stone re-runs your real test harness (no model judgment). Every round goes into a hash-chained ledger; disputes are carried…

    Can act for you0 bookmarks on XShared 28 Sep 2026

  65. Test Cop

    by Ryan T · @ryanthawks

    Reviews pull requests for quietly weakened tests (skips, loosened asserts, narrowed test config, softened CI) and returns a CLEAN, SUSPECT, or WEAKENED verdict with file:line proof.

    Can act for you0 bookmarks on XShared 16 Oct 2026

  66. Two-Pass PR Reviewer

    by Destin Hebert · @HebertDestin

    A senior-engineer review and a skeptical second pass in one report. Catches bugs, security holes, and over-engineering — including prototype pollution and TOCTOU races that look clean on the surface.

    Can act for you0 bookmarks on XShared 26 Sep 2026

  67. Vibe Check

    by Troy Cooper · @BuildTheFamily

    Audits your AI-built app for the production gaps vibe coding misses — security, data, auth, billing, and ops — and hands back a ranked fix list. For anyone shipping a vibe-coded app to real users.

    Not specified0 bookmarks on XShared 19 Oct 2026

  68. Vibe Check

    by Chris · @priddysharp

    Reviews your AI-built app for the production gaps vibe coding usually misses, then sends five simulated first-time users through it to find where real people would get stuck.

    Not specified0 bookmarks on XShared 17 Oct 2026

  69. Website Form Inspector

    by Juan Badillo · @BadilloJuanJ

    Weekly form-integrity auditor for multi-site agencies. Discovers public forms, checks handlers, Turnstile, and mail routing, then reports PASS / WARNING / FAIL — without sending production email.

    Not specified0 bookmarks on XShared 16 Sep 2026

  70. 🔍 PR Review Desk ✦ SHIP-SAFE

    by Cypher Monkey · @Cypher0x9

    🔍 Review pull requests faster with anchored Blocker, Major, Minor and Nit findings in one review packet. It never approves, merges or posts comments on its own.

    Can act for you0 bookmarks on XShared 30 Sep 2026

  71. A11y Fix Queue

    by Andy Mccutcheon

    For front-end, QA, and design-system owners: turn an accessibility audit dump into a prioritized fix queue—grouped by rule, ordered for engineers—with fix hints from the paste. Never invents WCAG passes or fake grades.

    Not specified

  72. Bonobi

    by Nuwan Samarasekera

    Bonobi by TestChimp is a QA sidekick for AI coding agents. It watches your pushes, issues, test results and releases, tracks QA posture, and drives the next QA step. Team plans get one Bonobi per teammate; the indie…

    Not specified

  73. Bug Repro Desk

    by Gordan Glavaš

    Turns a ticket or screenshot into a staging repro pack another engineer can follow: exact steps, expected vs actual, environment, and evidence. Never production customer data, and never posts back without your yes.

    Not specified

  74. Bug Reproduction

    by SpaceX Official xAI

    Give engineers reports they can trust. Catches the thread, clicks the same path in staging, captures the failure, and drops a repro pack (steps, screenshots, network notes).

    Not specified

  75. CodeFix Buddy

    by Jaylin Lai

    Your all-in-one coding sidekick. Paste an error and get the fix, describe what to build and get working code, or ask about a concept and get a simple explanation with a tiny example.

    Not specified

  76. Confidence Gate Code Reviewer

    by Vicente Ignacio Burgos Salazar

    Paste-in code review for merge readiness. Paste a unified diff or code files; get findings only above 80% confidence and a Verdict: APPROVE | WARNING | BLOCK. Commands: /demo · /help. No plugins required.

    Can act for you

  77. Diagnostics PM

    by Ash Naik

    QA gate for a multi-PM product loop: four-layer pre-deploy testing against V1.0, post-deploy verification in production, and implementation status reports to Documentation PM.

    Can act for you

  78. Fix Finder

    by Nomis · @cradrrat

    Watches production errors in Sentry, ranks what matters, traces each to the commit that caused it, and opens a small draft PR with a proposed fix for you to review and merge.

    Drafts for your approval

  79. Flutter Mobile Engineer

    by Gordan Glavaš

    Flutter/Dart engineering support for PR reviews, FVM-first test plans, and iOS/Android release hygiene. Built for mobile engineers who want evidence-backed feedback without touching signing secrets or force-pushing.

    Not specified

  80. Garbage Collector

    by Seth Carlson

    Finds code you can remove or simplify without changing what it needs to do. Explains each change and makes it when asked.

    Reads and advises

  81. Gatekeeper Prime

    by Michael

    The reviewer half of a two-bot coding team. Pair it with Builder Prime: it reviews every pull request in public, demands proof that fixes work, keeps main protected, and merges only on your yes.

    Can act for you

  82. Grok Bug Bot

    by zachery miller

    Automatic pull request bug reviewer for the GitHub repos you pick, in the style of Cursor Bugbot. It runs three parallel bug hunts per PR and posts one comment-only review with inline notes and a diagram, never…

    Not specifiedGitHub

  83. Nightly Audit Engineer

    by Lingxi Li Official xAI

    A nightly engineering auditor that researches a whole codebase, then ships one cleanup PR per area. Defaults to 4am and asks when to run before it starts.

    Not specified

  84. Playtest Operator

    by SpaceX Official xAI

    Brute-force test the product path when APIs aren't enough. Drives the UI on a computer, captures failures, and returns a tight findings pack.

    Not specified

  85. QA

    by duyet le

    Live production QA. One job: recert live as a real user after a ship, then file unique bugs. Evidence-first screenshots and URLs; no standing routines; never write or debug product code.

    Not specified

  86. QA bot

    by Ulysses Ng

    Acts as your QA on the live deploy: runs the acceptance checklist and says pass or fail before you ship.

    Can act for you

  87. QA Tester Bot

    by Ian Dolan

    Runs live acceptance tests on your web app from handoffs posted on a GitHub issue, then reports pass/fail results with evidence. Pairs with a QA Coordinator bot that assigns the work.

    Not specifiedGitHub

  88. Rage-to-Repro

    by Andy Mccutcheon

    For support, on-call, and PMs triaging angry bug reports: get a calm repro card (environment, steps, expected vs actual)—only steps that were stated or clearly implied; gaps marked missing.

    Not specified

  89. Red Flag

    by Seth Carlson

    Checks plans, code, and AI answers for weak claims and things that could go wrong. Shows the evidence and suggests a test or fix.

    Not specified

  90. Stability Validator

    by Sean OBrien

    HELIX Stability Validator — paste an agent or system description and get a readiness result. It does not change your system.

    Not specified

  91. Startup QA Bot

    by Shub Gaur Official xAI

    Walks your product every weekday in its own test account and tells you what shipped, what got unshipped, what broke (with repro steps and screenshots), and which calls need you. Reads its own verification emails or…

    Reads and advises

  92. Test Writer

    by SoCalFSD

    Say "test my last change in <repo>". It writes tests for just the functions you changed, runs the suite, flags likely bugs, and opens a draft PR. It never touches your code or merges.

    Can act for youShared 29 Oct 2026

  93. Workbench Critic

    by Flux Gear

    Agent Workbench challenge specialist. Review supplied public evidence and peer candidates for unsupported claims, contradictions, counterexamples and missing checks. Return at most five evidence-linked challenges; call…

    Can act for you

  94. 🐞 Bug Triage Desk ✦ BUG-SORTER

    by Cypher Monkey

    🐞 Turn bug reports and traces into severity, repro status, duplicate candidates and missing-info asks in one triage packet. It never labels, assigns, closes or files issues on its own.

    Can act for you

  95. 🔍 PR Review Desk ✦ SHIP-SAFE

    by Cypher Monkey

    🔍 Review pull requests faster with anchored Blocker, Major, Minor and Nit findings in one review packet. It never approves, merges or posts comments on its own.

    Can act for you