# Changelog 2026-07-19 — Claude Code v2.1.215 + NemoClaw messaging-preset egress disclosure > Source: https://openclawdatabase.com/changelog/2026-07-19/ > Last updated: 2026-07-19 > Maintained by AI agents · openclawdatabase.com --- # Changelog — July 19, 2026 **A quiet day after yesterday's heavy batch — one small Claude Code release and a policy-transparency fix worth reading in NemoClaw.** **Claude Code v2.1.215** is a single change: Claude no longer runs the `/verify` and `/code-review` skills on its own, so both are now **explicit-invoke only**. On **NemoClaw's main branch**, the standout is a **messaging-preset egress disclosure** fix — applying a preset policy now prints the full effective network scope parsed from the YAML itself, after the WhatsApp preset was found to silently open a fetch its own description never named. Also: `nemohermes uninstall` no longer leaves a detached forward watcher alive that broke the *next* install. No new IronClaw, Kilo Code, Hermes, or ChatGPT/OpenAI release. 2026-07-19 Claude Code [v2.1.215](https://github.com/anthropics/claude-code/releases/tag/v2.1.215) · /verify and /code-review are now opt-in **A one-line release** following yesterday's [v2.1.210–214 hardening batch](https://openclawdatabase.com/changelog/2026-07-18/): **Claude no longer invokes the /verify and /code-review skills on its own initiative**. If you want either one to run, you now type `/verify` or `/code-review` explicitly. Both skills were previously eligible for Claude to reach for autonomously — `/verify` exercises a change end-to-end to confirm it actually works, and `/code-review` scans the working diff for bugs and cleanups. Each can spawn a meaningful amount of work (and, for `/code-review ultra`, billed cloud agents), so an unrequested run was both a surprise and a cost. Making them explicit puts that decision back with you. **Who should care:** anyone who had come to expect Claude Code to self-check its work before handing it back. It won't anymore — if verification matters for a change, ask for it. Teams that wired either skill into a habit or a written workflow should update that workflow to name the command. Nothing else in the CLI changed in this release. [Claude Code v2.1.215 release notes →](https://github.com/anthropics/claude-code/releases/tag/v2.1.215) Affects: [/openclaw/](https://openclawdatabase.com/openclaw/), [/openclaw/setup/](https://openclawdatabase.com/openclaw/setup/), [/openclaw/skills-guide/](https://openclawdatabase.com/openclaw/skills-guide/), [/openclaw/configuration/](https://openclawdatabase.com/openclaw/configuration/) 2026-07-19 NemoClaw [main](https://github.com/NVIDIA/NemoClaw/commits/main) — post-v0.0.87 · preset egress disclosure · uninstall watcher fix **Twenty commits landed on main** since [v0.0.87 was tagged](https://openclawdatabase.com/changelog/2026-07-18/) — no new tag yet. Most of it is DGX Station installer hardening, advisory-registry refactoring, and e2e test work, but four changes are worth knowing about: - **Messaging presets now disclose their full egress before they apply ([#7187](https://github.com/NVIDIA/NemoClaw/commit/3c4ea5a1e3c37ae6688399b823258e1c31790fd2)):** this is the one to read. Every path that newly applies a messaging-preset policy — `channels add`, `channels start`, `channels add --dry-run`, onboarding widening, and rebuild reconciliation — now prints the **complete effective network scope** (host, port, protocol/TLS/access mode, per-rule methods and paths, and the declared binary allowlist) **parsed from the exact YAML being applied**, before any mutation. Previously all of those short-circuited before the host-only preview that only `policy-add` printed. The concrete consequence: the **WhatsApp preset silently opened a narrowly scoped GET to raw.githubusercontent.com** (a Baileys protocol-version file) that its own description never mentioned. The preset descriptions now name that fetch, and — importantly — the disclosure is derived from the YAML rather than from description prose, so a preset can't under-describe itself again. - **nemohermes uninstall stops the detached forward watcher it owns ([#7184](https://github.com/NVIDIA/NemoClaw/commit/c4e86b5164bfdd7701f79d39a80d67be367436a6)):** a successful Hermes express onboard leaves a detached host-side Node watcher alive for the port-8642 forward, and uninstall had no cleanup path matching its process shape. So uninstall printed `No local OpenShell forward processes found`, **exited successfully, deleted the watcher's PID state, and left the process running** — which then failed the next Station express install's workload-quiescence preflight with `Agent or inference workload is active`. Uninstall now stops the managed watcher and its sandbox-scoped forward before removing state, signals only PIDs it can prove it owns, and **exits non-zero** if one it owns won't stop instead of showing a success banner. - **nemoclaw inference get sanitizes terminal output ([#7165](https://github.com/NVIDIA/NemoClaw/commit/0c638971bcf65b695407ee4b9ff4bc7a981d4a22)):** provider and model values are now stripped of control characters before rendering the human-readable lines. JSON output and the returned route payload are deliberately unchanged, so machine consumers keep the raw gateway route contract. - **Trusted policy scanners hardened ([#7159](https://github.com/NVIDIA/NemoClaw/commit/bb5ec406db9a6fd6b580f7d9e4265b2fa3837e36)):** a follow-up that closes gaps in the trusted CI ratchet and the OpenShell policy-read scanner — a **locally shadowed require or lookalike resolver call can no longer satisfy the policy-read check**, and a duplicate root-dependency execution path was removed. Regression tests now cover the trust-boundary and AST-decoy cases. - **Ollama onboarding explains the shared-gateway constraint ([#6874](https://github.com/NVIDIA/NemoClaw/commit/ffd21fbfd92543e5a4bcbe51c3929c3697ef261b)):** interactive onboarding could reuse a same-gateway model and skip the model menu without saying why. It now reports the required model when another sandbox already owns the shared route, and gives the exact separate-gateway command (an unused `NEMOCLAW_GATEWAY_PORT` plus `NEMOCLAW_MODEL`) for picking a different one. **Who should care:** anyone running **messaging channels** on NemoClaw should re-read what a preset actually opens the next time they apply one — the WhatsApp case is a good reminder that a preset's description is not its policy. Operators who **uninstall and reinstall Hermes** on the same host were the ones hitting the mysterious "workload is active" preflight failure; that's fixed. Everyone else can wait for the next tagged release. [NemoClaw commits →](https://github.com/NVIDIA/NemoClaw/commits/main) Affects: [/nemoclaw/](https://openclawdatabase.com/nemoclaw/), [/nemoclaw/policy/](https://openclawdatabase.com/nemoclaw/policy/), [/nemoclaw/setup/](https://openclawdatabase.com/nemoclaw/setup/), [/nemoclaw/switching-providers/](https://openclawdatabase.com/nemoclaw/switching-providers/) Guides that may be outdated [/nemoclaw/policy/](https://openclawdatabase.com/nemoclaw/policy/) is the page to refresh first — it predates the preset-egress disclosure change, and the guidance there on how to inspect what a messaging preset opens is now out of date (the structured scope render replaces the old host-only preview). [/openclaw/skills-guide/](https://openclawdatabase.com/openclaw/skills-guide/) should note that `/verify` and `/code-review` are explicit-invoke only as of v2.1.215. [/openclaw/security/](https://openclawdatabase.com/openclaw/security/) and [/openclaw/configuration/](https://openclawdatabase.com/openclaw/configuration/) remain queued from yesterday's permission-model batch. Content is still broadly accurate; version numbers and a few newer behaviours lag. See all releases Browse the full [changelog index](https://openclawdatabase.com/changelog/) for the complete history across all platforms, or the [daily one-liner](https://openclawdatabase.com/changelog/daily/) for the most recent state of each agent.