# Additional Resources

URL: https://developertoolkit.ai/en/resources/
Description: Where to go when Claude Code, Codex or Cursor breaks, confuses you or changes: triage steps, doctor commands, and the FAQ, troubleshooting and changelog pages.

The Resources section is the help desk for Claude Code, Codex and Cursor: the FAQ for quick answers, Troubleshooting for errors, What's New for release and model changes, Community for people, and Feedback for bug reports. When an agent that worked yesterday breaks, the usual suspects are a version, config or permission change, so the triage steps come first.

You are halfway through a task, the agent that worked yesterday now refuses a tool call or cannot see your MCP server, and a forum thread suggests a flag you have never heard of. This page is for developers and tech leads in that moment: it tells you which page answers your question and how to prove a fix worked before you trust it again.

## Which resource page answers your question?

| Your situation | Go to | What you get |
| --- | --- | --- |
| An error message, a crash, a missing MCP server | [Troubleshooting guide](/en/resources/troubleshooting/) | Per-tool fixes, MCP connection checks, recovery procedures |
| "Do vendors train on my code?", "Is this on my plan?" | [Frequently asked questions](/en/resources/faq/) | Short, dated answers on models, plans, privacy, permissions, review and limits |
| Something behaves differently since last week | [What's new](/en/resources/whats-new/) | Month-by-month record of releases, model changes and breaking changes |
| You need a human, a maintainer or a shared skill | [Community resources](/en/resources/community/) | Where maintainers answer, and how to vet community fixes |
| A reproducible bug, or a mistake in this guide | [Provide feedback](/en/resources/feedback/) | Bug reports maintainers can reproduce, and how to report an error here |
| A term, flag, config key or shortcut | [Appendices](/en/reference/) | [Glossary](/en/reference/glossary/), [command reference](/en/reference/command-reference/), [configuration reference](/en/reference/config-reference/), [keyboard shortcuts](/en/reference/keyboard-shortcuts/) |
| "Which model is the default?", which model to use, and what it costs | [AI model comparison](/en/ecosystem/models/) | The only page on this site that carries model versions and prices |

## Triage an agent that stopped working

Do these in order. Each step rules out a cause before you touch config by hand.

1. **Record the exact version.** Advice for one release is often wrong for the next. Write the version down before you search.

2. **Run the tool's health check** (commands below). Fix what it reports first.

3. **Compare against the changelog.** Open [What's new](/en/resources/whats-new/) or the vendor changelog and look for changes between the last version that worked and the one you run.

4. **Search the [troubleshooting guide](/en/resources/troubleshooting/)** for the exact error text.

5. **Only then ask the community or file a bug**, with the version and the health-check output attached.

**Claude Code**

```bash
# terminal
claude --version
claude doctor    # checks the installation; reads settings in this directory without a trust prompt
claude update    # installs an available update
```
Inside a session, `/doctor` runs the fuller checkup that can also fix issues. Claude Code ships on two release channels: `latest` and `stable`, which is typically about a week behind. A fix or feature announced for `latest` may not exist on `stable` yet. See the [Claude Code changelog](https://code.claude.com/docs/en/changelog).

**Codex**

```bash
# terminal
codex --version
codex doctor --json   # installation, config, auth and runtime health, as a redacted report
codex update          # updates Codex to the latest version
```
The `--json` report is redacted, so you can attach it to a bug report. See the [Codex release notes on GitHub](https://github.com/openai/codex/releases).

**Cursor**

Record the version from Cursor's **About** dialog, then compare it with the [Cursor changelog](https://cursor.com/changelog) and the Cursor section of the [troubleshooting guide](/en/resources/troubleshooting/). This guide does not list a Cursor health-check command: none was verified on 2026-09-26.

The commands were checked against Claude Code 2.1.283 and Codex CLI 0.157.1. For every other command and flag, see the [command reference](/en/reference/command-reference/).

## Prompts that diagnose before they change anything

Both prompts work in Claude Code, Codex and Cursor. They make the agent collect evidence first and edit nothing until you choose.

**Copy-paste prompt: find what an update broke**

```text
My agent setup stopped working after an update. Do not edit any file yet.
1. Print the CLI version and the output of its doctor command, if it has one.
2. List every settings, instructions (CLAUDE.md, AGENTS.md, rules) and MCP config file loaded in this session, with its path.
3. If you can read the tool's changelog, list each change since the previous version that touches a file, key or flag from step 2.
Report a table: file or flag, change, likely effect, how to confirm. Then wait for me to pick the row to fix.
```

**Copy-paste prompt: vet a fix from a forum thread**

```text
The fix pasted below comes from a forum thread. Before applying it:
- List every file, flag, setting or environment variable it changes.
- Check each flag and key against --help or the config schema of the version installed here, not from memory, and mark any that do not exist.
- Flag anything that widens permissions, disables a sandbox, skips approvals, or adds a hook or MCP server.
- Propose the smallest reversible way to try it and the command that proves it worked.
Apply nothing until I confirm.
```

## How do you prove a fix worked?

Do not trust a fix because the agent says it worked. Prove it with signals you do not have to read line by line:

- The health check (`claude doctor`, `codex doctor`) comes back clean.
- The exact task or command that failed now succeeds, run fresh in a new session.
- Your project's own gates pass: tests, type check and lint.
- `git diff --stat` shows changes only in the config files you expected.

A tech lead adds one more step: record the version, the symptom and the fix in the team's shared instructions or runbook, so the next person does not debug it again.

## When help pages and community fixes mislead you

- **The advice was written for another version.** A flag that was renamed or removed fails with "unexpected argument" or is silently ignored. Recovery: check `--help` for your version and the [command reference](/en/reference/command-reference/), which lists stale flags to remove.
- **A "fix" that turns off safety.** Threads often suggest `--dangerously-skip-permissions`, `bypassPermissions` or `--dangerously-bypass-approvals-and-sandbox`. These hide the symptom and remove the guardrail. Recovery: revert, and use them only in a disposable, network-restricted sandbox.
- **You updated mid-task.** A new release can change defaults, such as the permission mode an interactive session starts in. Recovery: finish or checkpoint the task, update, then re-run the health check before you continue.
- **The FAQ and the changelog disagree.** The changelog is newer. Trust the dated primary source, then [report the mismatch](/en/resources/feedback/) so the page gets fixed.

## Where to go next from Resources

- [Developer track](/en/start/developer/) — The reading path from your tool's quick start to reviewing evidence instead of diffs
- [Power-user tips](/en/start/power-user-tips/) — One-line tricks for Claude Code, Codex and Cursor, each linked to its full page
- [Skills, MCP servers or plugins](/en/ecosystem/) — Choose the right extension point, then find its ecosystem shelf
- [Troubleshooting guide](/en/resources/troubleshooting/) — Per-tool fixes, MCP checks and recovery procedures