> ## Documentation Index
> Fetch the complete documentation index at: https://scanaislop-update.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Deterministic auto-fix for mechanical slop

> Mechanically fix reversible and low-risk findings, then use aislop agent or a prompt handoff for issues that need judgment.

`aislop fix` is the deterministic cleanup layer. It applies mechanical fixes first - unused imports, narrative comments, formatting, dead code - and can still print or open a structured prompt for older agent handoff flows. For the full local repair workflow with worktrees, provider setup, verification, sessions, and optional PR publishing, use [`aislop agent`](/cli/agent).

## Fix workflow

Work through the stages in order to reach 100/100 with the least disruption to your codebase:

<Steps>
  <Step title="Run a plain scan to see everything">
    Before touching anything, get the full picture.

    ```bash theme={null}
    aislop scan
    ```
  </Step>

  <Step title="Apply only reversible fixes with --safe">
    Start conservatively. `--safe` restricts the run to fixes that cannot change behaviour: unused-import removal,
    import merging, narrative-comment removal, and formatting. Apply these, review the diff, and commit.

    ```bash theme={null}
    aislop fix --safe
    ```
  </Step>

  <Step title="Run the standard auto-fixer">
    Without `--safe`, aislop also clears console-log leftovers, removes dead code, and runs lint autofixes. Review
    the diff before committing.

    ```bash theme={null}
    aislop fix
    ```
  </Step>

  <Step title="Run aggressive fixes with --force">
    `--force` adds dependency auditing, framework alignment checks, and unused-file removal. These are more
    disruptive, so review the diff carefully.

    ```bash theme={null}
    aislop fix -f
    ```
  </Step>

  <Step title="Hand off remaining issues to your agent">
    For the full local repair loop, run `aislop agent`. For prompt-based handoff, pass the remaining diagnostics to
    your coding agent with full diagnostic information:

    ```bash theme={null}
    aislop agent # recommended local repair workflow
    aislop fix --claude # Claude Code
    aislop fix --codex # Codex CLI
    aislop fix --cursor # Cursor (copies prompt to clipboard)
    aislop fix --gemini # Gemini CLI
    aislop fix -p # Print prompt (agent-agnostic)
    ```
  </Step>

  <Step title="Verify with a final scan">
    Confirm everything is resolved.

    ```bash theme={null}
    aislop scan
    ```
  </Step>
</Steps>

## Flags

<ParamField query="-d, --verbose" type="boolean">
  Show detailed progress for each fix operation as it runs, including which files are modified and which rules are
  being resolved.
</ParamField>

<ParamField query="-f, --force" type="boolean">
  Run aggressive fixes in addition to standard ones. This includes dependency auditing, framework dependency
  alignment, and unused-file removal. Changes here are more likely to affect behaviour—review the diff before
  committing.

  ```bash theme={null}
  aislop fix -f
  ```
</ParamField>

<ParamField query="--safe" type="boolean">
  Restrict the run to reversible fixes only. Safe mode applies:

  * Unused-import removal
  * Import merging
  * Narrative-comment removal
  * Formatting

  Anything that deletes code or rewrites behaviour—console removal, dead-code elimination, lint autofixes,
  unused-declaration pruning, and dependency changes—is skipped. A `--safe` run is designed to be "apply and commit"
  without review.

  ```bash theme={null}
  aislop fix --safe
  ```
</ParamField>

<ParamField query="-p, --prompt" type="boolean">
  Print an agent-ready prompt to stdout describing the remaining issues, without opening any specific agent. Use this
  flag when you want to paste the prompt into any tool or inspect it first.

  ```bash theme={null}
  aislop fix -p
  ```
</ParamField>

## Prompt handoff flags

When auto-fix can't resolve an issue and you do not want the full `aislop agent` workflow, pass the remaining diagnostics to your coding agent. Each flag opens that agent and provides the structured prompt automatically. Use `--prompt` / `-p` if you prefer an agent-agnostic output you can paste anywhere.

<Tabs>
  <Tab title="Terminal agents">
    | Flag         | Agent         |
    | ------------ | ------------- |
    | `--claude`   | Claude Code   |
    | `--codex`    | Codex CLI     |
    | `--gemini`   | Gemini CLI    |
    | `--kimi`     | Kimi Code CLI |
    | `--opencode` | OpenCode      |
    | `--aider`    | Aider         |
    | `--goose`    | Goose         |
    | `--pi`       | pi            |
    | `--crush`    | Crush         |
    | `--amp`      | Amp           |
    | `--warp`     | Warp          |
  </Tab>

  <Tab title="Editor agents">
    | Flag            | Agent                                 |
    | --------------- | ------------------------------------- |
    | `--cursor`      | Cursor (copies prompt to clipboard)   |
    | `--windsurf`    | Windsurf (copies prompt to clipboard) |
    | `--vscode`      | VS Code (copies prompt to clipboard)  |
    | `--antigravity` | Antigravity                           |
    | `--deep-agents` | Deep Agents                           |
  </Tab>
</Tabs>

<Tip>
  Use `--prompt` (`-p`) to print the agent handoff prompt without opening any specific tool. You can then paste it
  into any agent, share it with a teammate, or inspect the diagnostics before deciding what to do next.
</Tip>

## What --safe restricts

`--safe` is designed for situations where you want to improve the score with zero risk of introducing bugs. The table below shows what runs and what is skipped:

| Fix type                   | `--safe` | Standard `fix` | `fix -f` |
| -------------------------- | :------: | :------------: | :------: |
| Unused-import removal      |     ✅    |        ✅       |     ✅    |
| Import merging             |     ✅    |        ✅       |     ✅    |
| Narrative-comment removal  |     ✅    |        ✅       |     ✅    |
| Formatting                 |     ✅    |        ✅       |     ✅    |
| Console-log removal        |     —    |        ✅       |     ✅    |
| Dead-code elimination      |     —    |        ✅       |     ✅    |
| Lint autofixes             |     —    |        ✅       |     ✅    |
| Unused-declaration pruning |     —    |        ✅       |     ✅    |
| Dependency auditing        |     —    |        —       |     ✅    |
| Framework alignment        |     —    |        —       |     ✅    |
| Unused-file removal        |     —    |        —       |     ✅    |

## Common examples

```bash theme={null}
# See what's fixable before touching anything
aislop scan

# Apply only safe, reversible fixes
aislop fix --safe

# Standard auto-fix with detailed output
aislop fix -d

# Aggressive mode: deps, unused files, all autofixes
aislop fix -f

# Run the local repair workflow for remaining issues
aislop agent

# Or hand off remaining diagnostics to Claude Code
aislop fix --claude

# Print the agent prompt without opening any tool
aislop fix --prompt

# One-off run without installing
npx aislop@latest fix --safe
```