Verified change intelligence for developers and founders who run agents. We track consequential releases, pricing, limits, reliability, security, and compatibility—then explain what changed, what could break, and what to do next.
Registry stats loading…
We separate release-note language from the behavior, policy, price, limit, or compatibility change that matters in practice.
We look for pricing changes, migration risk, reliability regressions, security exposure, and hidden operational limits before recommending an update.
Each report ends with a practical verdict: update, wait, test first, pin a version, change configuration, or ignore the announcement.
Claude Code v2.1.271 (2026-09-14 22:12 UTC) ships eight capabilities and ~40 fixes. Headline capability: fast mode now applies in Claude Code Remote sessions (cloud and self-hosted runners), gated by org policy. Headline security: per-command allowed_domains to sandboxed Bash/PowerShell/Monitor in auto mode, and managed-mcp.json now keeps exclusive MCP control when unparseable (fail-closed). Headline safety net: --host-config-snapshot disk|memory prevents self-hosted runners from silently losing all host config when the directory exceeds 64 MiB. Plus: six Bash permission-check bypasses closed (fmt/column, wildcard expansion, variable flag, two-cd+subshell), three org-policy cache fixes (credential switch, tool-list refresh, ANTHROPIC_UNIX_SOCKET proxy), four MCP fixes (list_changed tight loop, OAuth registration race, bare-name tool search, Ctrl+O reconnect), two --resume fixes (1M context drop on model-family mismatch, file-read tracker inheritance), four fast-mode fixes (org-disabled off, CLAUDE_CODE_SKIP_FAST_MODE_ORG_CHECK rejection persistence, retry-watchdog fallback, credential-mid-session), one skills cleanup (claude.ai-synced skills move to recoverable trash at sign-out if older than cleanupPeriodDays). v2.1.272 two hours later: bug fixes only, treated as NOVELTY_LOW.
We do not rewrite launch posts. We connect primary sources, reproducible tests, scanner evidence, Registry records, and technical guides to the decision in front of you.
Pricing, policy, security, compatibility, and incident claims start with official documentation, repositories, advisories, or status pages. Community reports are labeled as experience, not proof.
Field reports name the version, environment, method, inputs, and limitations. If we only compared documentation, we say so.
The skills and MCP Registry remains free. Its source links, scan states, provenance, and explicit evidence gaps help test whether an ecosystem claim survives contact with real artifacts.
Durable technical guides and inspectable workflow manifests turn a news event into implementation work you can adapt and validate in your own environment.
A guide to dependency review, supply-chain risk triage, and remediation workflows.
A practical walkthrough of Model Context Protocol server structure, authentication, and tool registration.
A technical guide to turning SEO findings into concrete implementation work.
Codex, Claude Code, Gemini CLI, Cursor, OpenClaw, Hermes, MCP, models, memory, orchestration, and agent infrastructure—prioritized by cost, limits, reliability, security, compatibility, and practical capability.
Weekday impact reports, a weekly Before You Update brief, and tested comparisons when the evidence supports them. No quota filler.
The intelligence index is the canonical feed. Existing articles and payload URLs remain available while new coverage follows the evidence-first format.
Open the intelligence index