# AI Agents · Tech watch [Canonical source]() Systems using models to choose actions, call tools and perform tasks. ## [Reticle gives coding agents a verdict on the running app]() Reticle helps coding agents check what they actually built rather than stopping at the code change. The repository presents a runtime-perception tool for web and desktop apps; `reticle compare` drives two builds in a browser and reports differences users can see, network calls, and console errors. Verification happens from outside the app, with no SDK required. The comparator can pit a main build against a pull request preview and, with `--base`, classify differences as regressions, missed targets, or changes. 2026-11-08 · [Markdown]() · [Original resource]() ## [Fimo automates website maintenance and search visibility]() Fimo helps marketing teams maintain a website and improve its visibility in search engines and AI answers with specialized agents for SEO, GEO, content, performance, accessibility, and compliance. The platform also includes a visual editor, hosting, previews, and change history. Agents run on a schedule or when the site changes. Small fixes can publish automatically; changes that need a decision arrive as proposals with previews for approval. The site stays connected to its existing framework without being rebuilt, while developers continue working in the code. 2026-11-07 · [Markdown]() · [Original resource]() ## [Taste Skill gives coding agents design rules and browser checks]() Taste Skill gives coding agents a system for building less generic company websites: palettes, hero layouts, UI fragments and real photographs, with art direction tailored to the type of business. The repository offers Claude Code and Codex integrations, plus installation through `npx skills`. Its distinctive feature is automated checking in headless Chrome: pages render at four widths, from 390 to 1440 px, and are checked for empty visuals, contrast, alignment and images missing on slow networks. WebGL and scroll effects are limited to tech, gaming and software pages, with static fallbacks for phones and reduced motion. 2026-11-06 · [Markdown]() · [Original resource]() ## [Pullboard coordinates AI agents with specs and independent verification]() Pullboard coordinates development agents around approved specifications: each claims an item in its own worktree, passes a test gate, then another agent verifies the commit before it is accepted. Rules and activity stay in the repository, with a local board instead of a hosted service. Its workflow puts concrete controls around agent work: approved requirements are frozen when an item is claimed, lanes restrict writable paths, and a state machine shared by the commands, interface, and documentation governs each transition. 2026-11-03 · [Markdown]() · [Original resource]() ## [AI agents to find exposed personal data and request its removal]() A three-agent workflow aims to find exposed personal data, identify removal procedures, and draft GDPR requests. The document sets out each agent’s role and instructions, then explains how to have them collaborate in a Cue group chat. The process keeps human approval before emails are sent and says never to share passwords. It also distinguishes sites that catalogue data breaches from the organizations responsible for them, helping avoid contacting the wrong party. 2026-11-03 · [Markdown]() · [Original resource]() ## [Cloudflare Security Audit Skill structures agent-led audits]() This skill turns a coding agent into a security auditor by orchestrating a six-phase repository audit, from reconnaissance to report generation. Findings are structured as machine-readable data and independently verified. A separate agent tries to disprove each candidate; results distinguish confirmed findings, leads needing validation, and rejected candidates. Running target code requires an OS-enforced sandbox with external networking disabled and resource limits in place. 2026-11-02 · [Markdown]() · [Original resource]() ## [Agent loops in C\# with Microsoft Agent Framework]() Agent loops combine action, observation, and evaluation to refine an answer or retry an operation until it meets a criterion. Jesse Liberty demonstrates the pattern in C# with Microsoft Agent Framework: a loop agent, an evaluator, and an iteration limit. The example contrasts a deterministic marker such as `DONE` with a model-based judge, then outlines safeguards to add: timeouts, idempotent calls, logging, and cost tracking. Each iteration adds latency and token usage. 2026-11-02 · [Markdown]() · [Original resource]() ## [Elephant-Goldfish Model: Google’s skills for shaping specs]() Elephant-Goldfish Model, Google’s open-source plugin, provides **skills** to explore an idea, draft a specification, and challenge it before implementation. An “Elephant” agent keeps the project context; “Goldfish” reviewers inspect the document without the conversation history to surface unstated assumptions and risks. The repository also covers resolving review findings and comparing documentation with code. Reviews require fresh subagent contexts; if the environment cannot create them, EGM stops that step. 2026-11-01 · [Markdown]() · [Original resource]() ## [Modern Web Guidance brings current web practices to coding agents]() Modern Web Guidance gives coding agents expert guidance on browser APIs, CSS, performance, and accessibility, steering them toward native solutions instead of legacy patterns. The repository brings together 232 features and 186 use cases as skills installable in multiple agents. Its CLI searches locally for a guide and adds it to the agent’s context. The guidance incorporates Baseline compatibility data, targeted fallbacks, and automated evaluation; the project is marked as a preview release. 2026-11-01 · [Markdown]() · [Original resource]() ## [Microsoft Agent Framework: choosing where to intercept calls]() In Microsoft Agent Framework, `ChatClient` middleware intercepts messages exchanged with the LLM, while agent middleware operates on the agent’s overall run, including session, identity, or token-budget management. This distinction helps place logging or modification at the right level. The C# example adds function-invocation middleware to log calls to the Researcher agent’s Tavily tool, without changing the other agents. The trace shows the function name and its arguments. 2026-11-01 · [Markdown]() · [Original resource]() ## [TanStack DB 1.0 RC1: using test oracles to harden agent-written code]() TanStack DB reaches 1.0 RC1 after extensive stabilization work. Kyle Mathews explains how **test oracles**—independent models that calculate expected behavior—and property-based testing uncovered bugs in collection updates and the change messages sent to subscribers. These executable references also give coding agents precise rules to preserve when changing the implementation. The trade-off is clear: writing and refining models takes work, but their simplicity makes complex algorithms easier to verify. The RC also supports incremental adoption, from existing REST APIs to local persistence, offline mutations, and real-time sync. 2026-10-30 · [Markdown]() · [Original resource]() ## [TanStack AI 1.0 stabilizes its core; the agent harness remains experimental]() TanStack AI 1.0 stabilizes its core APIs for combining chat, tools, media, and integrations across multiple providers and UI frameworks. Tree-shakable adapters and end-to-end tests using deterministic fixtures check the flows without live model calls. The agent harness adds durable sessions, interrupts, and background work, but remains 0.x and may change in minor releases. Upgrading requires moving the stable packages together and supplying a `threadId` explicitly; passing the type check does not migrate persisted conversations or files. 2026-10-30 · [Markdown]() · [Original resource]() ## [WebMCP: W3C backs a polyfill for experimenting with web agents]() The W3C has launched a second pilot in its open-source program: a polyfill for WebMCP, an incubating JavaScript API that lets applications expose functions as tools callable by agents and assistive technologies. The polyfill is intended to support experimentation and interoperability as the specification evolves. Plans include publishing an npm package, tracking Web Platform Tests coverage, and advancing lifecycle events and declarative support. If WebMCP moves onto the standards track and interoperable native implementations emerge, the polyfill would be phased out gradually. 2026-10-29 · [Markdown]() · [Original resource]() ## [oh-my-hermes: coordinating models, skills, and verification]() oh-my-hermes adds an orchestration layer to Hermes Agent: it maps work categories to models and reasoning effort, loads skills on demand, and can turn a goal into a graph of parallel tasks. Each task keeps a separate write scope, while a distinct node verifies the outcome. A notable architectural choice is **separating preparation from execution evidence**: a plan is not treated as completed work, and an agent’s claim that it finished does not validate the result. The project also offers review-gated memory and a dedicated TUI, without replacing or patching Hermes Agent. 2026-10-28 · [Markdown]() · [Original resource]() ## [Archify turns a question into an interactive HTML map or page]() Archify is an open-source Agent Skill that helps an AI agent turn a description, question, or repository evidence into an **interactive diagram** or a concise page with a clear conclusion and sources. It supports ten diagram types, from architecture maps to timelines, and outputs a self-contained HTML file with no runtime dependencies. Maps can be explored and refined in plain language, without learning a diagram editor. For one-page answers, sources can be pinned to a specific commit; the result can also be exported as a long image or PDF. The skill works with Claude Code, Codex, Cursor, OpenCode, and GitHub Copilot. 2026-10-27 · [Markdown]() · [Original resource]() ## [React: making UI states explicit in the agentic era]() When an agent changes a UI, checking a single account cannot cover every role, plan, or feature flag. Matt Rothenberg shows how values scattered across hooks, providers, and layouts can hide overlooked states — such as a Delete button shown to a view-only user. Making display state an explicit component input lets teams render relevant combinations directly, test them, or compare them in a visual grid. Storybook and Playwright complement this approach, but they do not choose which scenarios to cover; that decision still matters. 2026-10-27 · [Markdown]() · [Original resource]() ## [Chums brings Claude Code and Codex to Apple Watch]() Chums connects an Apple Watch and iPhone to Claude Code or Codex agents running on a Mac. Its interface makes agent activity visible, shows tool calls, and lets users respond to permission requests or dictate instructions. The Node.js hub stays on the Mac, but the watch API is exposed through Tailscale Funnel and protected by a token. The project is open source and requires no Chums account, though setup involves building the apps with Xcode and configuring several dependencies—a trade-off between local control and a more demanding installation. 2026-10-25 · [Markdown]() · [Original resource]() ## [Claude SEO brings multi-agent SEO audits to Claude Code]() Claude SEO turns Claude Code into an SEO auditing tool: specialist agents assess indexing, performance, content, structured data and visibility in AI search, then produce a prioritized action plan. Reports stay on the machine, but analyzed pages are sent to Claude, as with other Claude Code workflows. The repository also emphasizes tooling reliability, with automated checks, support for Python 3.11 through 3.14, and safeguards against untrusted web content. Live-data extensions are optional; without Google API keys, Core Web Vitals results are lab estimates. 2026-10-24 · [Markdown]() · [Original resource]() ## [Vercel Shop speeds up a Shopify storefront with Next.js]() Vercel Shop pairs a Next.js storefront with Shopify, which remains responsible for the catalog, payments, and checkout. Cache Components serve product data quickly, then stream personalized content; meanwhile, the cart updates before the server responds through an optimistic UI. The template adds agent-facing options: an opt-in shopping assistant, skills for extending the store, and Markdown served through the `Accept` header. It offers a concrete starting point for these flows while keeping Shopify as the commerce engine. 2026-10-23 · [Markdown]() · [Original resource]() ## [Agent skills: preserve flexibility while supplying context]() PostHog shares practical guidance for writing skills that help agents without locking them into a brittle workflow. The core idea is to load context progressively, define the goal and constraints, then let the agent choose steps that fit the repository and runtime environment. The article also addresses maintenance: separate durable structure from fast-changing details, point to a single source of truth, and regenerate skills instead of patching them indefinitely. Skills carry context and upkeep costs, so they make most sense for recurring tasks where agents lack essential context or perform poorly by default. 2026-10-23 · [Markdown]() · [Original resource]() Page 1 / 3 [Next]()