verification plugins

by Junseok Pak

Incremental verification for coding agents: propose complete test shards, rerun affected checks, and reuse authoritative passing evidence with optional Guarded approval boundaries.

by CodeTruss

The deterministic first-pass verification gate for AI-written code.

by Jason-chen-coder

A 13-skill team development suite for Codex: dev-auto, dev-grill-docs, dev-spec as a compatibility alias, dev-plan, dev-tdd, dev-fix, dev-image-to-code, swagger-doc-skill, dev-verify, dev-code-review, dev-commit-writer, dev-finish, and dev-design-context.

by Aria Han

KERNEL is a Claude Code and Codex runtime for direct, decomposed execution with local memory and minimal hooks. Version 9.11.0 deploys the simplify deletion doctrine, preflight and verifier contract. Skills invoke as /kernel:<name> on Claude Code and $kernel:<name> on Codex; run /kernel:help first. Agent-readable summary: llms.txt.

by MailAgent

Temporary inboxes for Codex OTP, magic links, and signup QA flows.

by MailAgent

Temporary inboxes for Codex OTP, magic links, and signup QA flows.

by Yiming Wu

Structured guardrails for AI coding: brainstorm, plan, execute, review, and verify.

by luoxianzi

Command the legion, judge the work — Claude plans, Codex executes, and a binding fresh-context judge decides what merges. Zero config.

by Yonatan Gross

Portable OrchestKit workflows for Codex: brainstorm, explore, implement, assess, verify, review pull requests, and render inline diagrams with glyph.

by Yonatan Gross

Portable OrchestKit workflows for Codex: brainstorm, explore, implement, assess, verify, review pull requests, and render inline diagrams with glyph.

by Lauren Tan

Find what a diff breaks beyond the diff and prove the one safety fact by running real code instead of writing it up.

by Junseok Pak

Incremental verification for Claude Code: rerun affected checks, reuse authoritative passing evidence with revision-aware receipts, and keep an optional Guarded approval boundary for higher-risk work.

by Junseok Pak

Incremental verification for coding agents: propose complete test shards, rerun affected checks, and reuse authoritative passing evidence with optional Guarded approval boundaries.

by rjk

Truth-verified file editing for AI coding agents via MCP

by Agent Bounties contributors

Find verified claimable bounties, earn from digital work, post or fund bounties, and check canonical Base USDC evidence.

by Zerker Labs

Portable, cryptographically signed receipts for everything Claude Code does. Proof that stays true after the session ends.

by Dwarves Foundation

Spec-driven workflow with shared Claude Code and Codex guardrails.

by Hamza Ali

A reusable, stack-agnostic website launch system: a verification-gated checklist (Done ≠ Verified), a refuse-to-launch sign-off gate, a Day 1/3/7/14/30 monitoring cadence, an anonymized failure-mode library, and programmatic-SEO-at-scale quality gates. Routes to specialist SEO/security plugins for commodity crafts.

by GeckoVision

Comprehend any API or Solana program into first-call-correct agent tools, and check the call before it counts: simulate the exact bytes, predict compute, refuse on stale evidence.

by Synapti AI

Evidence-first project documentation system. Produces an audit-ready 23-file package for technical due diligence, engineering and product onboarding, and partner or customer communication — every material claim traced to a ledger row and a claim state, three context-isolated verification passes, and a binary release gate. Ships a post-merge GitHub Actions job that keeps the package current by opening a documentation PR. Requires bash, git and jq; on Windows, Git Bash (see docs/windows-support.md).

by Mamdouh Abo Ammar

Portable coding lifecycle for AI agents: deterministic routing, research, planning, test-first changes, delegation, verification, review, security, release, handoff, evaluation, and recovery across 27 canonical skills.

by JadeYingWah

Delivery-discipline behavior overlay for AI agents: a pre-implementation gate, resource survey, evidence discipline, and hands-on acceptance. Model-agnostic; it disciplines process, it does not raise the reasoning ceiling.

by baleen37

AI coding assistant toolkit - git workflow protection, verification, shipping, research, and development automation

by Marat Karimov

Catalyst: disciplined agentic development - SDD pipeline with decision-boundary model tiering, spec hardening, premortem gates, verification, and handoffs.