Article by **Chase Covington**, **Tomer Slaney** (partners, New York) and **David Pralong** (senior partner, Charlotte), published by the *McKinsey Transformation Practice* in **September 2026** (exact day unspecified, dated the 1st by convention); 8 pages, 2 exhibits whose content is not reproduced in the text. **(1)** Finding: the transformation office (TO) is slow to modernize its own tools; in a turnaround involving **3,000** employees, **more than 15** people produced a **300-page** report every four weeks. **(2)** Three pillars entrusted to agents: *performance intelligence*, *single source of truth*, *conversation facilitation*. **(3)** Reported gains: **35 to 40%** of time on core tasks, sometimes **70%**; a central team reduced from **ten to three** people. **(4)** Guardrails: cascading errors between agents, false alerts, traceability of each step. **(5)** Sequence: reporting first, action automation next, change management within the TO. The authors present the text as "a first look at the opportunity for TOs". The cases are not named, no measurement method is described, and two of the tools cited (**Wave**, **Lilli**) belong to McKinsey. The text follows on from [[sternfels-mckinsey-60000-people-20000-agents-officechai-2026-01-14]], where McKinsey already counts its agents among its workforce.
Announcement from **Google** on **August 6, 2026**: Google joins as **Core Maintainer** the **Agent Plugins 1.0.0** specification, an open, *vendor-neutral* packaging format for distributing **Agent Skills** and **MCP servers** together. The specification was published by a **TSC** whose Core Maintainers come from **Amazon, Cursor, Microsoft, OpenAI, and Vercel**; Google joins them, represented by **Kevin Hou** (Senior Staff Engineer, Google DeepMind). The two packaged building blocks — Agent Skills and MCP — originate from **Anthropic**, which does not appear on this list of maintainers. **The diagnosis** fits in one sentence: *"The core problem isn't the components. It's the manifest."* A skill is portable, an MCP server is portable; the box they go in is not, and every client had to invent it for itself — hence the forks, the copies of identical components, and their drift. **The format** fits in one constraint: *"A plugin is a directory. That's the whole idea, and the restraint is the point."* A `plugin.json` with two useful lines (`$schema` and `name`), skills in `skills/` in the Agent Skills format, servers declared in `mcp.json` with an **explicit `type` on each entry** (stdio, Streamable HTTP, or the legacy HTTP+SSE) — no more transport guessed from the shape of the config object. The strength of the design lies in what the manifest **cannot** do: neither relocate components nor declare them inline, so there is no discovery path to configure and no precedence order to learn. Operational corollary: components **fail independently** — an `mcp.json` server that fails to start does not take down the plugin's skills, the client skips the entry, keeps going, and reports the failure. The accepted escape hatch is the **reverse-domain** directory (`com.example.client/`), an extension space owned entirely by one client (hooks, agents, commands) that other clients ignore: *"the portable core stays small because the non-portable parts have somewhere legitimate to go."* A section is dedicated to cases where the format is not warranted — *"Not every skill should be a Plugin"*: a single MCP server to a single client, `mcp.json` suffices; a single skill needs no plugin. What v1 explicitly excludes, under *future considerations*: **no installation mechanism, no distribution protocol, no permissions model, no sandboxing requirement, no trust or provenance verification, no UX**. All of this fits into an independently adoptable four-layer stack — **find** (Agentic Resource Discovery), **describe** (AI Catalog, which would register the `application/agent-plugins+json` type), **package** (Agent Plugins), **run** (MCP + Agent Skills). Two Google products already ship: **Agents CLI** and **Data Agent Kit** (BigQuery, Spanner, Cloud SQL).
SFEIR analysis (firm's voice) of the general availability, on July 9, 2026, of **GPT-5.6** by OpenAI — not a single model but a **family of three tiers**: **Sol** (long-horizon/cyber/science flagship, the only one to unlock the "max" and "ultra" modes), **Terra** (everyday balanced tier, ~half the price of GPT-5.5), and **Luna** (fast/economical, high volume). All three share ~**1.05M tokens** of context, **128k** output tokens, and a knowledge cutoff of **February 16, 2026**. The most structuring fact is not a score but an **aggressive pricing grid** (Sol $5/$30, Terra $2.50/$15, Luna $1/$6 per million tokens): Sol keeps the previous flagship's price while being more capable, forcing the comparison onto the **capability-to-cost ratio**. Two billing subtleties (cache writes billed at **1.25×**, a surcharge beyond **272k** tokens) make the grid misleading until one has measured how much context the agent re-reads (read/write ratio ~**153:1** in agentic coding). Engineer's verdict, claimed to be neutral (SFEIR is both a **Google Cloud Premier** partner *and* an **Anthropic** partner): **no one sweeps every table** — GPT-5.6 dominates Terminal-Bench 2.1 and the Coding Agent Index (at a third of the cost per task), Claude stays ahead on SWE-Bench Pro (~15 pts); METR flagged a record **reward hacking** rate on Sol. Conclusion: "stop looking for the champion, learn to route" — the model is a commodity, the durable advantage lies in **Context/Harness Engineering**.
**Zed** blog post signed by **Franciska Dethlefsen** (head of growth and marketing), published on **May 14, 2026** — the day after Anthropic's announcement — to answer Zed users' questions. **Subject**: starting **June 15**, Anthropic **splits Claude subscription billing into two pools** — one for its **first-party tools** (chat, the official Claude Code CLI), the other for **third-party agent and SDK usage** (anything going through **ACP**, `claude -p`, or a third-party tool). Usage via ACP **then stops drawing from the Pro or Max limits** and switches to a monthly **"Agent SDK" credit**: **$20 for Pro, $100 for Max 5x, $200 for Max 20x**. Once the credit is exhausted, usage continues **at standard API pricing** if overage is enabled — otherwise requests stop until the next cycle. **The figure driving the article**: subscriptions had until then subsidized agentic usage by a factor of **≈15 to 30×** relative to API pricing, and the new credits are billed **at full API rates** — hence *« for anyone using agents heavily, this is a major cost increase »*. **Three options are proposed**, in an order that reveals Zed's position: (1) keep the subscription by running the **official `claude` CLI in a terminal inside Zed** rather than via ACP — *« when the official claude CLI runs in the terminal, it uses your subscription's limits, not the new credit »*; (2) use Zed's built-in agent with the provider of one's choice (Zed-hosted models, API keys, Copilot, local Ollama, DeepSeek); (3) plug in **any ACP agent** — OpenCode, Codex, Factory, Cursor —, several of which still offer rate-limited subscriptions that subsidize heavy usage. **The underlying thesis**, and the real reason for the post: *« ACP is an open protocol… so that your editor is never locked into one provider's pricing decisions »*, with the explicit anticipation that *« this kind of change won't be the last »*. **The post carries an addendum dated June 16, 2026** announcing that **the change is suspended**: ACP, `claude -p`, the Agent SDK, and third-party applications continue to work with subscriptions **as before**, no separate credit to claim, limits unchanged, Anthropic revising its plan with advance notice announced. **The artifact is thus self-contradicting**: its most important content — the reversal — postdates its own publication date by a month.
#Zed#Anthropic#Claude subscription
**Franciska Dethlefsen** — head of growth and marketing chez **Zed Industries**. Le rôle est déterminant pour lire le texte : ce n'est pas un billet d'ingénierie mais une **communication de crise produit** · écrite le lendemain d'une annonce d'un fournisseur dont Zed dépend · à destination d'utilisateurs inquiets. La signature growth/marketing explique la structure (problème → options → réassurance) et le fait que l'argument protocolaire arrive en conclusion plutôt qu'en tête.
Podcast by Greg Isenberg × Meng To (designer, founder of Design+Code, creator of the products Aura / New Form / Dream Cut) on **`design.md`** — Google's open-source convention, equivalent to `agents.md` / `skills.md` / `soul.md` but **for the design system** (typography, colors, spacing, WebGL/Three.js animations, reveal rules). Central idea: carrying the "**soul of design**" in a markdown file that is handed to an agent (Claude Code, Codex, OpenClaude, Gemini, Stitch, Aura, V0, Lovable, Cursor) to preserve **cross-medium consistency** (web, mobile, Replit slides, Hyperframes/Remotion motion design). Triad taught: **HTML = finished dish, design.md = recipe, skills = ingredients** (typography, lasers, skeuomorphic, 3D skills — 63 in New Form). Major diagnosis: **design drift** on one-shot workflows (`v0`, Lovable, Framer) that start strong then drift into generic output. Meta-message: *taste* is the only remaining **moat** — *"if something looks like another thing, its value drops by 10× to 100×"*. Workflow: **Reference → Design.md → Generate → Inspect → Systemize → Iterate (up to 1000+ prompts) → Remix → Expand → Export**. Critique of **purple gradients** ("you just run") as the generic post-vibe-coding baseline. Meng To claims to have spent ~$500,000 in tokens, run 1,000–10,000 iterations per product, and managed 4 products in parallel solo.
#design.md#Google#design system
Greg Isenberg (host — podcast Late Checkout / The Greg Isenberg Show, 12 mai 2026 livestream workshop ideabrowser.com) ; **Meng To** (guest — designer, fondateur Design+Code 2014, créateur Aura / New Form / Dream Cut, autodidacte parti à 18 ans, dropout, francophone d'origine canadienne)
Analyst note by **Mitch Ashley**, VP and Practice Lead for *CIO & Technology Buyers* and *Software Lifecycle Engineering* at **The Futurum Group**, published on **April 29, 2026** in the *Market Coverage News* section: short format, roughly **9,500 characters**, opening with five summary bullets and closing with five watch-list items. Subject: the deal announced on **April 21, 2026** under which **SpaceX** gains the right to acquire **Cursor** for **$60 billion** within the year, or to pay **$10 billion** for a compute partnership backed by **xAI**'s **Colossus** cluster in Memphis, described as equivalent to **1 million H100 GPUs**. (A) The two-need reading: Cursor was carrying both a compute ceiling and margin compression — the company pays market-rate prices for **Anthropic**'s and **OpenAI**'s models, which it routes to its customers while competing with them via its **Composer** line; SpaceX was seeking AI revenue and a narrative ahead of an IPO targeted for June. (B) The structure reading: a $10 billion floor and a $60 billion purchase option exercisable in publicly traded stock after the listing, which, Ashley writes, *"allocates risk more honestly than a straight acquisition."* (1) For buyers, it sets a **six-month** window to re-verify zero-data-retention clauses and vendor identity. (2) For providers, it distinguishes three exposures — **Google** shielded by **Antigravity**, **AWS** dependent on Anthropic, **IBM** lightly exposed but well positioned on the governance angle. The corpus already holds [[beck-starving-genies-usage-limits-ai-coding-2026-04-03]] on the resource constraint imposed on coding tools and [[nyt-musk-promises-spacex-ipo-track-record-2026-06-02]] on SpaceX's announcements.
#SpaceX#Cursor#Anysphere
Mitch Ashley · VP et responsable des pratiques CIO & Technology Buyers et Software Lifecycle Engineering chez The Futurum Group · ancien CIO et CTO.
FinOps for AI Agents: A Four-Step Allocation Framework for Coding Assistant Costs (Claude Code, Cursor, Copilot) and Why Traditional Cloud Tagging Fails - Finout