Original URL: https://getagenttools.com/blog/ WRITING # Notes from running agents What actually ships, what gets cut, and why. Verdicts from daily use, not press releases. ### [opencode --dangerously-skip-permissions: a hidden alias for --auto, and what deny rules still stop](https://getagenttools.com/blog/opencode-dangerously-skip-permissions/) 23 Oct 2026 opencode accepts --dangerously-skip-permissions as a hidden alias for --auto. What it approves, what deny rules still block, and the permission config in opencode.json. - opencode - coding-agents - agent-security ### [Codex dangerously skip permissions: --dangerously-bypass-approvals-and-sandbox and the safer pair](https://getagenttools.com/blog/codex-dangerously-skip-permissions/) 20 Oct 2026 Codex has no --dangerously-skip-permissions. Use --dangerously-bypass-approvals-and-sandbox, or -a never with a sandbox. Plus approval\_policy, sandbox\_mode and --approve-for-me. - codex - coding-agents - agent-security ### [GA4 consent mode: the sessions your banner hides, measured against Search Console clicks](https://getagenttools.com/blog/ga4-consent-mode/) 17 Oct 2026 GA4 consent mode explained: basic vs advanced, what each sends before the click, and a store where Search Console counted clicks on days GA4 counted nothing. - measurement - ad-platforms - field-notes ### [RAG vs Fine Tuning: Choose by Facts, Behavior and Evaluation](https://getagenttools.com/blog/rag-vs-fine-tuning/) 11 Oct 2026 Choose RAG or fine-tuning by the failure you need to fix: missing facts, inconsistent behavior, or both. Includes a decision worksheet and a local retrieval fixture. - rag - fine-tuning - llm-evaluation ### [n8n error handling: catch failures without repeating the action](https://getagenttools.com/blog/n8n-error-handling/) 10 Oct 2026 Use n8n error workflows, node error outputs and bounded retries. A local receipt model shows why a timeout can repeat an action that already succeeded. - automation - agent-tools - reliability ### [Claude Code Sandbox: Check File and Network Boundaries Before a Run](https://getagenttools.com/blog/claude-code-sandbox/) 9 Oct 2026 Configure the Claude Code sandbox, probe file and network restrictions, and check retries, excluded commands and tools that run outside its boundary. - claude-code - agent-security - agent-ops ### [Claude Code Channels: Incoming Events, Access and Session Limits](https://getagenttools.com/blog/claude-code-channels/) 8 Oct 2026 Understand Claude Code Channels, sender allowlists, session lifetime and permission relay. Use a local test plan before connecting an external chat platform. - claude-code-channels - claude-code - agent-security ### [AI Agent Cost: Measure Cost per Successfully Completed Task](https://getagenttools.com/blog/ai-agent-cost/) 7 Oct 2026 Calculate AI agent cost with tokens, tools, retries, failed tasks and operator time. A synthetic ledger shows what cost per successful task includes. - ai-agent-cost - agent-operations - evaluation ### [Claude Code Checkpoints: Rewind Edits and Check Recovery Limits](https://getagenttools.com/blog/claude-code-checkpoints/) 6 Oct 2026 Choose code, conversation or both in Claude Code rewind, check shell and subagent limits, and keep Git and external recovery separate from checkpoints. - claude-code - agent-ops - git ### [Claude Code Worktrees: Isolate Parallel Changes and Merge Them](https://getagenttools.com/blog/claude-code-worktrees/) 5 Oct 2026 Use Claude Code worktrees for parallel tasks, choose the right base, handle dependencies, review each branch, merge changes and clean up safely. - claude-code - agent-ops - git ### [Claude Code Plugins: Install, Inspect, Update and Remove One Cleanly](https://getagenttools.com/blog/claude-code-plugins/) 4 Oct 2026 Choose a Claude Code plugin scope, inspect its components and context cost, diagnose loading, then update, disable or remove the correct installation. - claude-code - skills - agent-ops ### [Codex Skills: Build a Reusable Workflow and Check It Loads](https://getagenttools.com/blog/codex-skills/) 3 Oct 2026 Build a small Codex skill with SKILL.md, choose its local scope, check discovery, and test explicit invocation without assuming tool access. - codex-skills - codex - agent-workflows ### [GPT-6.1 Sol arrives: dots, Codex plans and what the limits mean](https://getagenttools.com/blog/gpt-6-1-sol-dots-codex-plans/) 29 Sep 2026 GPT-6.1 Sol is here. Check dots access, ChatGPT Pro prices, Codex usage limits and the difference between faster modes and billing multipliers. - codex - agent-tools - agent-ops ### [Claude Sonnet 5.5: the same token prices, a different migration checklist](https://getagenttools.com/blog/claude-sonnet-5-5/) 28 Sep 2026 Claude Sonnet 5.5 keeps Sonnet 5 token prices. Check speed claims, API changes, and progress updates your agent interface could stop showing after migration. - claude - agent-ops - coding-agents ### [Own your intelligence: an honest scorecard for my AI agent stack](https://getagenttools.com/blog/own-your-intelligence/) 25 Sep 2026 Harrison Chase's own-your-intelligence framework, checked question by question against my own AI agent stack, with honest yes, no, and partial answers. - ai-strategy - agent-harness - ai-agents ### [Let AI agents review your code, but never let them merge in the dark](https://getagenttools.com/blog/ai-code-review-agents/) 24 Sep 2026 How to use AI agents for code review without losing control: specialized reviewer agents, a CI loop, fail-closed auto-merge gates, and verifying real behavior. - ai-code-review - agentic-ci - code-review-automation ### [Prompt caching, explained by someone who actually pays the bill](https://getagenttools.com/blog/prompt-caching-explained/) 23 Sep 2026 How prompt caching actually works under the hood, what is worth caching, when it does nothing for your bill, and the one-line check I run before turning it on. - llm-cost - prompt-caching - claude-api ### [The four types of technical debt in AI systems, and how to audit them](https://getagenttools.com/blog/ai-technical-debt/) 22 Sep 2026 AI technical debt breaks into four types: data, model, prompt, and organizational. Here's what each looks like in practice, plus a self-audit checklist. - ai-governance - technical-debt - ml-ops ### [Opus 5.5, GPT-6 Sol and Luna: what launched and what changes for agents](https://getagenttools.com/blog/opus-5-5-gpt-6-sol-luna/) 22 Sep 2026 Opus 5.5, GPT-6 Sol and Luna launched September 22, 2026. Compare API IDs, token prices, Work and Codex availability, and migration checks for agent builders. - ai-models - agent-tools - claude - codex ### [Smart zone / dumb zone: where the useful part of your agent's context window ends](https://getagenttools.com/blog/smart-zone-dumb-zone/) 21 Sep 2026 Context rot explained: why a large context window does not stop an agent from getting worse mid-session, plus how to spot the dumb zone and four ways out. - context-window - agent-context-management - claude-code - context-engineering ### [Your AGENTS.md is a router, not the whole project documentation](https://getagenttools.com/blog/agents-md-is-not-your-documentation/) 20 Sep 2026 AGENTS.md and CLAUDE.md files bloat when every fix gets appended to them. A router-first structure, plus what OpenWiki automates, keeps the entry file small. - agent-documentation - context-engineering - claude-code ### [Google Merchant Center feed: seven things a 550,000-item feed had wrong before the first ad](https://getagenttools.com/blog/google-merchant-center-feed/) 19 Sep 2026 Google Merchant Center feed audit: what a 548,575-item feed had wrong (empty MPN, constant availability, missing images) and which fixes actually moved. - ad-platforms - measurement - field-notes ### [claude --resume: what a resumed session restores, what it drops, and what my cheat sheet got wrong](https://getagenttools.com/blog/claude-resume/) RUNNING 18 Sep 2026 claude --resume from the Claude Code docs: when to resume, when to /clear, what a resumed session restores and what it drops, from 215 transcripts on disk. - claude-code - agent-ops - context-engineering ### [--dangerously-skip-permissions: what it skips, what still stops Claude, and the dead allowlist](https://getagenttools.com/blog/dangerously-skip-permissions/) TESTED 16 Sep 2026 --dangerously-skip-permissions: what it skips, what deny rules and hooks still block, and the matching switch in Codex, opencode, Cursor, Copilot and Gemini CLI. - claude-code - agent-security - agent-ops ### [claude -p: the flag that turns Claude Code into a build step, and what it costs](https://getagenttools.com/blog/claude-p-headless/) 13 Sep 2026 claude -p runs Claude Code with no terminal: prompt in, result out, JSON with cost and session ID. The flags my automations use and what --bare changes. - claude-code - agent-ops - coding-agents ### [What is an agent harness? The code around the model that decides what actually runs](https://getagenttools.com/blog/what-is-an-agent-harness/) 12 Sep 2026 What is an agent harness: every piece of code around the model, the loop, the tools, the approvals and the log. Examples, harness vs agent, and the one I run. - glossary - agent-harness - agent-ops ### [Claude Code context window: what fills it before you type, and the 33 edits I wasted in July](https://getagenttools.com/blog/claude-code-context-window/) 11 Sep 2026 Claude Code context window explained from the docs: what loads at startup, what /context shows, when auto-compaction runs, what survives, and the rules I keep. - claude-code - context-engineering - agent-ops ### [What is function calling? The structured request a model returns instead of running code](https://getagenttools.com/blog/what-is-function-calling/) 10 Sep 2026 What is function calling: the model picks a tool and writes the arguments, your code runs it and sends the result back. The loop, the cost, and MCP. - glossary - agent-tools - mcp ### [Claude Code memory: what 538 auto memory files taught me about the 200-line index](https://getagenttools.com/blog/claude-code-memory/) 9 Sep 2026 Claude Code memory has two parts: CLAUDE.md you write and auto memory Claude writes. Where each lives, the 200-line and 25 KB limits, and my 538 memory files. - claude-code - context-engineering - agent-ops ### [What is a system prompt? The instructions loaded before you type](https://getagenttools.com/blog/what-is-a-system-prompt/) 8 Sep 2026 What is a system prompt: the instructions an application loads before your message, what they can and cannot enforce, and how Claude Code builds its own. - glossary - prompt-engineering - llm ### [Claude Code subagents: two files, 125 dispatches, and the work that never touched my context](https://getagenttools.com/blog/claude-code-subagents/) 7 Sep 2026 Claude Code subagents run a task in their own context window and return a summary. What the docs guarantee, the two agent files I run, and one leaked .env file. - claude-code - agent-ops - context-engineering ### [What are AI guardrails? The controls that hold when the model has a bad day](https://getagenttools.com/blog/what-are-ai-guardrails/) 6 Sep 2026 What AI guardrails are in operator terms: input filters, output checks and action gates, why the third one is the one agents need, and the three layers I run. - glossary - guardrails - agent-security ### [claude --chrome: field notes on letting Claude Code drive my own browser, and where it breaks](https://getagenttools.com/blog/claude-chrome/) 5 Sep 2026 Field notes on claude --chrome, the flag that hands Claude Code your logged-in browser: 27 screenshot timeouts, clicks that miss, and the gates I use. - claude-code - browser-automation - agent-ops ### [ChatGPT Ads: the platform is real, the measurement is what I would test first](https://getagenttools.com/blog/chatgpt-ads/) WATCHING 4 Sep 2026 ChatGPT Ads: a US test in February, self-serve in 52 countries by September. What Ads Manager Beta gives you: bids, context hints, Pixel and Conversions API. - ad-platforms - chatgpt - measurement ### [What is RAG in AI? The lookup step that runs before the model answers](https://getagenttools.com/blog/what-is-rag/) 4 Sep 2026 What is RAG in AI, in plain terms: fetch relevant text from a source you chose, put it in the prompt, then generate. How it works, RAG vs MCP, where it fails. - glossary - llm - rag ### [PreToolUse: the hook that reads every command before my agent runs it](https://getagenttools.com/blog/pretooluse-hook/) 3 Sep 2026 Before a tool call runs, a PreToolUse hook in Claude Code can deny it or ask me. My 79-line production guardrail, the ssh case rules miss, and its limits. - claude-code - agent-ops - guardrails - agent-security ### [What is an AI agent? A model, tools, a loop and a human at the gate](https://getagenttools.com/blog/what-is-an-ai-agent/) 2 Sep 2026 A plain definition of what an AI agent is: a language model that picks tools inside a loop, with a stop condition and a human on the gates that matter. - glossary - ai-agents ### [statusLine: the Claude Code status line I rebuilt after a 13-second render](https://getagenttools.com/blog/statusline-claude-code/) 1 Sep 2026 The statusLine setting runs a script on every update. My claude code statusline reads only stdin: median 41 ms, replacing a tool that took 13-20 s a render. - claude-code - agent-ops - context-engineering ### [AI agent architecture diagram: the six layers I actually run](https://getagenttools.com/blog/ai-agent-architecture-diagram/) 31 Aug 2026 A practical AI agent architecture diagram with six layers for goals, orchestration, context, models, tools, policy, and production observability in practice. - ai-agents - architecture - agent-ops ### [LLM evaluation: the small test stack I trust before production](https://getagenttools.com/blog/llm-evaluation/) 30 Aug 2026 A practical LLM evaluation method using representative test cases, deterministic checks, human review, calibrated model judges, and release gates that work. - llm - evaluation - testing ### [7 AI agent examples that actually do work](https://getagenttools.com/blog/ai-agent-examples/) 29 Aug 2026 Seven practical AI agent examples with their inputs, tools, stop conditions, human approval gates, and the failures each design must handle in production. - ai-agents - use-cases - field-notes ### [What is a prompt? The instruction you give an AI model](https://getagenttools.com/blog/what-is-a-prompt-in-ai/) 28 Aug 2026 A plain explanation of AI prompts, their main parts, prompt roles, practical examples, common mistakes, and how to test whether a prompt works in practice. - glossary - prompt-engineering - llm ### [MCP server security: the trust boundaries I check first](https://getagenttools.com/blog/mcp-server-security/) 27 Aug 2026 A practical MCP server security checklist covering trust boundaries, credentials, token handling, approvals, sessions, sandboxing, and logs for AI agents. - mcp - agent-security - security ### [What is a context window in AI? The limit that changes agent behavior](https://getagenttools.com/blog/what-is-an-ai-context-window/) 26 Aug 2026 What is a context window in AI? Learn what fits inside it, how it differs from memory, why long context still fails, and how agents manage it in practice. - glossary - llm - context-engineering ### [AI agent deployment: the release path I use before production](https://getagenttools.com/blog/ai-agent-deployment/) 25 Aug 2026 AI agent deployment needs more than a working prompt. Use this practical path through sandbox, staging, canary release, monitoring, rollback, and approval. - ai-agents - deployment - production ### [What is an AI hallucination? Why models make things up, and what actually helps](https://getagenttools.com/blog/what-is-ai-hallucination/) 24 Aug 2026 What is an AI hallucination: a fluent, confident output that is not true. Why next-token prediction makes them inevitable, and which defenses work. - glossary ### [The AI time dividend should go to tests, not more features. Mine did not, at first](https://getagenttools.com/blog/ai-time-dividend-tests/) 23 Aug 2026 Agents write code many times faster. Robert C. Martin says spend the saved time on testing rigor. Field notes on what that looks like when you actually do it. - coding-agents - agent-ops ### [What is a token in AI? The unit your whole bill is written in](https://getagenttools.com/blog/what-is-a-token/) 22 Aug 2026 What is a token in AI: the chunk a model reads and writes text in. Roughly three-quarters of a word, and the unit behind every context limit and every invoice. - glossary ### [AI agent monitoring in production: traces, cheap judges, and the loop that compounds](https://getagenttools.com/blog/ai-agent-monitoring/) 21 Aug 2026 AI agent monitoring is not server monitoring. Field notes from running a 36-probe cockpit over an agent fleet: traces, review queues, judges, decision stamps. - agent-ops - production - monitoring ### [Slack Code: multiplayer coding also means a multiplayer prompt](https://getagenttools.com/blog/slack-code-channels/) WATCHING 21 Aug 2026 Slack Code gives coding agents their own channels with diffs, previews and a self-archiving log. What it changes for permissions, prompts and who can build. - coding-agents - agent-ops - agent-security ### [What is an LLM? The engine under every AI agent, minus the mysticism](https://getagenttools.com/blog/what-is-an-llm/) 20 Aug 2026 What is an LLM: a model trained on text to predict the next token, and the engine under chatbots and agents. How it works in practice and what people get wrong. - glossary ### [disable-model-invocation: the flag that keeps my deploy skills out of Claude's hands](https://getagenttools.com/blog/disable-model-invocation/) 19 Aug 2026 One frontmatter line decides if Claude can run a skill on its own. disable-model-invocation on 55 real skills, 0 flagged then 8, plus Copilot, Cursor, Codex. - context-engineering - agent-ops ### [What is AI? A plain answer for people who have to buy, use or approve it](https://getagenttools.com/blog/what-is-ai/) 18 Aug 2026 What is AI, in plain language: software that handles judgment calls, learned from data instead of programmed. What the term covers, and the myths around it. - glossary ### [I audited my CLAUDE.md against Anthropic's new context engineering rules](https://getagenttools.com/blog/claude-md-audit/) 17 Aug 2026 Anthropic cut over 80% of Claude Code's system prompt. The new CLAUDE.md best practices, tested against a real 482-line config and its 26 loudest rules. - context-engineering - agent-ops ### [Production-ready AI agents: the 12 gates to pass before real access](https://getagenttools.com/blog/production-ready-ai-agents/) 14 Aug 2026 A production-readiness checklist for AI agents: 12 gates across access, actions, failure and operations, each with a failure mode and a pass or stop test. - agent-ops - production - guardrails ### [DeepSeek Harness: everything is a plugin, except the parts that are not](https://getagenttools.com/blog/deepseek-harness/) WATCHING 13 Aug 2026 DeepSeek Harness ships under MIT with every capability as a plugin. What the docs let you swap, what they will not, and the tools left switched off. - agent-harness - coding-agents - open-source ### [Writing your own MCP server: the code is the easy part, the tool descriptions are not](https://getagenttools.com/blog/build-your-own-mcp-server/) 11 Aug 2026 When an MCP server integration is worth writing yourself, what it takes, and why tool descriptions cost more thought than code. Notes from two servers I run. - mcp - agent-tools - agent-security ### [Remote MCP servers: what changes when the server is not yours](https://getagenttools.com/blog/remote-mcp-servers/) 11 Aug 2026 Hosted and public MCP servers move the credential, the failure mode and the trust boundary off your machine. What I run, what broke today, what I check first. - mcp - agent-security - agent-tools ### [An MCP server for your database: what breaks when the agent gets the schema](https://getagenttools.com/blog/mcp-server-database/) 10 Aug 2026 An MCP server for your database gives an agent live SQL in minutes. Field notes on schema cost, read-only roles, and why my write path never goes through MCP. - mcp - databases - agent-security ### [Choosing an MCP server for AI agents: the criteria change when nobody is watching](https://getagenttools.com/blog/mcp-server-for-ai-agents/) 10 Aug 2026 An MCP server for AI agents is judged differently than one for chat: tool count, description quality, error text, blast radius, and the check I run first. - mcp - agent-tools - agent-security ### [An MCP servers list worth keeping: the eight I leave connected, and what gets removed](https://getagenttools.com/blog/mcp-servers-list/) 10 Aug 2026 An MCP servers list is only useful if it is short. The eight I keep connected, what earns a place, what gets one removed, and why directories do not help. - mcp - agent-tools - context-engineering ### [What is an MCP server in AI, and where does your data actually go?](https://getagenttools.com/blog/what-is-an-mcp-server-in-ai/) 10 Aug 2026 What is an MCP server in AI: host, client and server explained, both transports, and a plain answer to where your data ends up when an agent calls a tool. - mcp - agent-tools - context-engineering - glossary ### [Agent harness design: what Meta put in Muse Code, and what I already run](https://getagenttools.com/blog/muse-code-agent-harness/) WATCHING 6 Aug 2026 Agent harness design notes on Meta's Muse Code launch: an append-only event log, background agents that outlive the task, and an approval gate as a skill. - agent-harness - coding-agents - context-engineering ### [Field notes, not a directory](https://getagenttools.com/blog/field-notes/) RUNNING 26 Jul 2026 Why this blog only covers agent tools that carry real production work, and how the verdicts get decided. - agents - workflow