Field notes
Field notes on coding agents, leftover cloud infrastructure, and the bills that outlive the chat.
Latest
All articlesTreat each AI agent as its own principal—scoped tokens, delegated permissions, one-agent revoke. Compare Mintive, Okta Govern AI Agent Identity, and WorkOS Agent Auth; draw the boundary vs an MCP gateway.
Read article
Stop guessing from viral 'digital snitch' posts. Decide by account type whether self-assessment runs, what retention applies, how Cyber Verification handles research false positives, and why Claude Code telemetry is not server-side assessment.
Decide which file owns a third-party hook, which official unload removes it, and which managed hooks a user disable cannot turn off after an orchestrator or desktop installer rewrites Claude, Codex, Cursor, or Copilot config.
Decide which parallel-agent conflict class you are solving before spinning N worktrees. Compare deterministic intent claims (scope+operation), contract-first merges, ownership orchestration, and LLM mutual review—with Foremerge as a worked case, not a launch post.
Chrome ships fixes; Playwright pins Chromium later. Decide by workload—own-app E2E, agent untrusted browsing, Playwright MCP—using chromiumSandbox, channel chrome, non-root hosts, and egress allowlists. A decision matrix for Claude Code, Cursor, and MCP.
Public GitHub repos block pull_request_target by default on December 2, 2026, with brownouts on November 9 and 16. Inventory workflows, switch CI to pull_request, and allow the trigger only for jobs that never execute fork code.
Decide when a coding agent should share your real Firefox logins versus driving a separate automation browser. Compare Kitsune, firefox-bridge, Playwright MCP, and Claude in Chrome on session model, profiles, and approval gates—without pretending modes stop prompt injection.
Coding agents create VMs, databases, and deploys mid-task—then sessions end without teardown. A practical FinOps playbook for read-only audit, human-confirmed cleanup, Claude Code/Codex/MCP blind spots, and what --verify can (and cannot) prove.
A stub so the site has a second category. The FinOps essay is the real article on windtask.com.
2 articles
Writing filed under Developer Tools.
1 article
Cloud cost, orphan resources, and the habits that keep agent-created infrastructure from billing after the session ends.
1 article
Short site notes. This shelf exists so a second category has a real route.
1 article
Account-type decisions for AI retention and monitoring: what self-assessment actually runs, what stays, and what you can turn off.
4 articles
Browser freshness, containment, and the trust decisions coding agents make when they open pages you did not write.