Anthropic named the role: the Agent Manager — a hybrid PM/engineer single DRI who owns the Claude Code configuration that every developer in the org actually feels. Without that role, enterprise rollouts stall in phase two; with it, the model improving is no longer the bottleneck. ThumbGate is the pre-action runtime that role needs at the tool-call boundary.
| You own | ThumbGate ships |
|---|---|
| CLAUDE.md hierarchy Keeping the policy that the model reads on every session current and consistent across repos. |
Prevention rules distilled from repeated real 👎 feedback and written into CLAUDE.md by scripts/feedback-to-rules.js. A hosted org-wide rule library is not generally available. |
| Plugin marketplace Deciding which Claude Code / Cursor / Codex plugins are blessed and which are not. |
ThumbGate ships as a Claude Code plugin, a Cursor extension (Marketplace listing pending Cursor's review since 2026-05-19; runtime install works today via npx thumbgate init --agent cursor), a Codex plugin, and a Gemini CLI hook. One install, every supported agent. Adapter compatibility matrix kept current as runtimes change. |
| Permissions policy What an agent is allowed to execute, against which surfaces, with which evidence required. |
PreToolUse hooks at the tool-call boundary. Each block carries the rule that fired, the evidence that triggered it, and a reason the agent can use to choose a safer plan. No "tell the model to be more careful." |
| Which skills ship The set of in-context skills, prompts, and snippets every developer's agent has access to. |
Skill ship matrix in adapters/* — Claude, Cursor, Codex, Gemini, Amp, Cline, OpenCode. Each adapter is version-pinned and CI-checked against the upstream runtime. |
| Keep them current When Claude Code ships a breaking change to hooks or to the plugin API, your rollout cannot wait a quarter. |
Managed adapter maintenance for the supported personal runtime surfaces. Enterprise service work is fixed in a signed scope; it is not an unbounded hosted operator or 24×7 incident-response promise. |
Every enterprise Claude Code rollout hits the same wall: the model gets better, the setup does not, and nobody owns it. The teams that get past phase one and into actual adoption all turn out to have a single DRI behind CLAUDE.md, the plugin policy, the permissions, and the skill ship list. The teams that do not, stall.
Individual engineers install agents. CLAUDE.md is whatever they wrote. The Agent Manager role is unfilled or shared. ThumbGate enters as the free npx thumbgate init wedge — one repo, one repeated failure, one Pre-Action Check.
This is where the Agent Manager becomes a named role. The $499 Enterprise Workflow Gate scopes one repeated failure into one configured local gate, its regression test, and rollout and rollback proof. A hosted dashboard and org-wide hosted rule library are not generally available.
The team becomes the harness. The Agent Manager stops being a bottleneck because the policy enforces itself at the tool-call boundary. The configured gate and regression test keep the proven workflow from drifting as adoption spreads.
npx thumbgate init in one repo. Captures thumbs-up/down feedback locally; auto-promotes repeated failures into prevention rules.Anthropic named the role. ThumbGate is the runtime that role needs. The free CLI is real, MIT-licensed, and works locally. The $499 Enterprise Workflow Gate is the single managed entry offer for one supported workflow.