Developer Tools Codex plugins

Plugin name

AgentProof

Package name

agent-shipproof

Publisher description

See what the AI agents in a workspace can reach: agent manifests, instructions, declared tools, MCP servers, permission policy and public proof references. Inspection only. Free.

Publisher capabilities · listing

Record an instruction and an action before the agent acts Add the result to the same record Seal a memory so a later session can check whether it changed Read records, seals and an agent's public keys Read stamps, inclusion and consistency proofs, and the witness list

Publisher full description

Check whether an MCP server, agent, API, package, domain or business has public ECZ-ID Resolver proof, and read the ResultState and ReasonCodes without turning them into a score. The three read-only ECZ-ID Verifier tools are used when the host has the Verifier MCP server configured; otherwise the…

Publisher capabilities · listing

Audits up to 25 pages of a site from its homepage and sitemap, with robots.txt respected Returns failed rules grouped by priority with the affected pages, the fix and the documentation link Checks titles, descriptions… …, limited per day Checks local AI-search readiness: services, locations, prices, FAQ, schema, NAP, proof Checks llms.txt, llms-full.txt, an AI page, home links, and name, product and fact consistency Drafts an llms.txt from the site's own public pages for the owner to review Grades 12 AI-search chec…

Publisher description

…autonomous software team. Assign a Linear, Jira or GitHub issue to SHIP, and its autonomous coding agents plan, build, review and test the 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 i… …nd session logs. Send an instruction to the agent that runs next, or leave a note for it. Read the proof that 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 y…

Publisher keywords · listing

…te build a website create a website website creator website generator ai website generator landing page builder ai landing page builder app builder ai app builder web app builder mobile app builder no-code app builder no code website builder business website builder small business website build my w… …site plumbing business landing page plumbing business website design plumbing business website copy roofing company website roofing company landing page roofing company website design roofing company website copy real estate agency website real estate agency landing page real estate agency website d…

Publisher full description

Currents gives AI agents the test results your CI records, from Playwright, Vitest, Jest and more. Self-healing tests • Ask why a run failed and get the errors, stack traces, screenshots and traces behind it • Step thr… …e test, flaky ones included • Compare a pull request's runs with main to see what the change broke Proof of work for any change • Before-and-after screenshots, videos, Playwright traces and DOM snapshots from CI • A demo the agent records in a browser, saved as a run • Evidence links posted in the p…

Publisher full description

NetPilot is an AI agent for networks. From a plain-English prompt it designs, builds and validates real multi-vendor networks in your private network lab, a cloud VM with 15+ real network operating systems with contain… …what each command does. - Network design lab: turn a design into a running multi-vendor topology, proof of concept or digital twin. - Network testing lab: reproduce a fault in BGP, OSPF or EVPN, run a failure scenario, or build a reproduction for a vendor case. - Pre-change validation lab: test a c…

Publisher full description

…at coordinate directly with each other: phones, handhelds, gateways and site computers exchange messages, shared documents and service calls over Bluetooth LE, local Wi-Fi and a mesh of nearby devices, with a hosted relay when no local path exists. Teams use it to cut cloud round trips and custom in… …L-3.0-only, with a commercial license available from Offline Protocol, Inc. The OfflineID SDKs and Proof of Location (beta) are MIT. Shared types and identicons are ISC.

Publisher full description

Finds reusable agentic workflows inside repositories, decides what should become public Skills or runtime-backed capabilities, compiles portable Skill packages, installs a host-native workspace operations Skill for… …tes the package, builds deterministic ZIPs, and prepares reviewer evidence without confusing local proof with public approval.

Publisher full description

…p), (5) Leaked Secrets, API Keys & Git History, (6) Supply Chain, SCA/CVE & SBOM, (7) AI, LLM & MCP Agent Security (Prompt Injection, Tool Abuse), (8) Web3, Smart Contracts, Wallet Blind Signing & Cryptography, (9) Containers, Kubernetes, Cloud & IaC, (10) Mobile (APK/IPA) & Desktop (Electron/Tauri), (11) Deep AST Taint Tracking, Z3 Symbolic Proof & Binary Hardening, and (12) Live Website Security Testing + 3-Layer Real-World Impact Triage (False-Positive Elimination, Exploitability Proof & Copy-Paste Remediation Patch). Connect your own V…

Publisher keywords · listing

ai-agents evaluation attestations offline-verification

Publisher description

Index and stream onchain data for the questions finance teams actually ask: proof-of-reserves and circulating supply, stablecoin transfer and sanctions monitoring, deposit detection, cross-chain settlement tracking (CCTP), payment reconciliation, wallet balances and transactio… …t data including Polymarket fills, positions and PnL. Real-time pipelines, hosted subgraphs, and managed RPC across 150+ chains.

Publisher keywords · listing

agent-skills engineering workflow review planning

Publisher description

Mistake-proof your code, your pipeline, and your agents. Audits code for mistakes that are possible, designs APIs where misuse cannot be expressed, installs guardrails, and turns incidents into devices that prevent recurrence.

Publisher full description

…TML embeds. The assistant must preserve the returned policy, observation period, freshness and coverage. Profiles require owner sign-up; collection or unavailable states are reported without an invented score. Comparisons can be unavailable when policies or periods differ. For v7.5 receipts, Craft e… …r judgments of ability. Adoption counts are analytics identifiers, not verified people, revenue or proof of causal impact. Verification distinguishes recorded issuance, signature authentication and arithmetic replay; it does not independently verify source truth. No Chapa sign-in is required to use…

Publisher full description

…ion rules, severity, references, rejection status, and source timestamps. Check exact installed package versions against OSV advisories, discover supported ecosystems, and follow CVE updates with resumable checkpoints. This hosted, read-only connector requires no signup, OAuth, API key, or local ins… …th source evidence. Unknown or incomplete results are not clean results, and no known match is not proof of safety. It does not modify files, install updates, scan targets, or access private Casco customer findings. Only explicit tool arguments are processed. Dependency-check cache misses send packa…

Publisher full description

…l verification into your app without hosting machine-learning models. This plugin helps your coding agent connect the deepface.dev API, compare two face photos, generate face embeddings and handle verification results in your existing stack. It guides account signup and server-side key setup, then t… …PI. The account owner confirms their email and accepts the service terms. Facial similarity is not proof of identity or liveness.

Publisher description

Development OS packages an activation-resilient development session kernel plus coordinated meaning, perspective, proof, and execution specialists.

Publisher full description

…moe.edu.sg_interactive_<slug>.zip for unscored work. Outputs are source files and SLS-ready ZIP packages. The plugin does not host an LMS, provide a standalone tutoring service, or automatically connect to student records. Generic control use is not proof of mastery. Local browser/mock-LRS tests do not establish live SLS attribution or rendering; teachers must review and test their deployed activity.

Publisher description

…reject, with issues ranked by severity and suggested fixes. The verdict can come back as a signed proof that anyone can check later without trusting us. You can also verify a proof someone handed you (free), read the public verdict track record including the verdicts that turned out wrong (free), timestamp a third party's exact claim, reality-check a backtest, and audit an agent's verifiability. A verdict is a reasoned second opinion, not a guarantee of outcome.

Publisher full description

Develop and verify hardware with agents, from idea to board. Describe a device and the agent picks a board and parts from the catalog, wires them, writes the firmware, compiles it on a hosted toolchain and runs it on a simulated micr… …dio it can also flash and debug a real board. Simulation results are evidence about the model, not proof the circuit works on a physical board. Hardware the simulator does not model fails loudly instead of being faked. Sign-in with your LabWired account is required.

Publisher description

Agents can move work across ten projects at once. Your attention is one decision at a time. Project Desk closes that gap: many agents, many projects, one desk reflecting exactly what needs you next. A… …u can do: decisions, reviews, walks, and approvals. The Agent Queue holds scoped work with a clear proof of done. Because agent-ready work from every project gathers in one place, a single agent can keep making progress across your portfolio unattended — even overnight — without stopping at every ha…