Crit CLI

Crit CLI Reference

If a plan was just written and the user said /crit or crit, invoke the /crit command — do not use this reference skill. This skill covers CLI operations like crit comment, crit pull/push, and crit share.

Comments have three scopes:

• Line comments (scope: "line") — tied to specific lines, stored in files.<path>.comments
• File comments (scope: "file") — about a file overall, stored in files.<path>.comments with start_line: 0
• Review comments (scope: "review") — general feedback, stored in the top-level review_comments array

The review file path is shown by crit status.

Reading comments

When crit completes a review round, read stdout and follow its instructions. Unresolved comments are often embedded in that prompt as JSON. Check stderr for approved: true or approved: false.

When you need to read comments separately:

crit comments            # human-readable, unresolved only (default)
crit comments --json     # flat JSON for agents
crit comments --all      # include resolved comments
crit comments --plan <slug>   # plan reviews
crit comments [path]     # explicit review.json or .crit directory

Review-level comments are listed first — easy to miss in raw review.json. Uses the same review resolution as crit comment (--output, --plan, daemon session).

Multiple active sessions

When more than one review session matches the current directory and branch, headless commands (crit comment, crit comments, crit share, crit push, crit pull) refuse to guess. Run crit status (or crit status --json) to list every active session, then target the intended review with --session <id>:

crit comment --session <id> --author <name> <path>:<line> <body>
crit comment --session <id> --json --file comments.json --author <name>
crit comments --session <id>
crit share --session <id> <file>
crit push --session <id>
crit pull --session <id>

The JSON status output exposes the candidates in sessions.

{
  "review_comments": [
    {
      "id": "r_f1e2d3",
      "body": "Overall the architecture looks good",
      "scope": "review",
      "author": "User Name",
      "resolved": false,
      "replies": [
        { "id": "rp_b4a5c6", "body": "Thanks, addressed the minor issues", "author": "Claude" }
      ]
    }
  ],
  "files": {
    "path/to/file.go": {
      "comments": [
        {
          "id": "c_a1b2c3",
          "start_line": 5,
          "end_line": 10,
          "body": "Comment text",
          "quote": "the specific words selected",
          "anchor": "The sessions table needs a complete rewrite...",
          "author": "User Name",
          "resolved": false,
          "replies": [
            { "id": "rp_c7d8e9", "body": "Fixed by extracting to helper", "author": "Claude" }
          ]
        }
      ]
    }
  }
}

Field rules:

• resolved: false or missing — both mean unresolved. Only true means resolved.
• quote (optional): the specific text the reviewer selected — narrows scope within the line range. Focus changes on the quoted text rather than the entire range.
• anchor (line comments): full text of the commented lines when placed. When edits shift line numbers, locate content by anchor rather than trusting start_line/end_line.
• drifted: true: original content was removed or heavily rewritten — line numbers are approximate at best.
• Unresolved comments may have replies — read them before acting.

# Review-level (general feedback)
crit comment --author 'Claude Code' '<body>'

# File-level (whole file, no line numbers)
crit comment --author 'Claude Code' <path> '<body>'

# Line (single line or range)
crit comment --author 'Claude Code' <path>:<line> '<body>'
crit comment --author 'Claude Code' <path>:<start>-<end> '<body>'

# Reply to an existing comment
crit comment --reply-to <id> --author 'Claude Code' '<body>'

Hard rules:

• Always pass --author 'Claude Code' (or your agent name) so comments are attributed correctly.
• Always single-quote the body — double quotes break on backticks and shell metachars.
• Line numbers reference the file on disk (1-indexed), not diff line numbers.
• Reply bodies support markdown — use code fences and inline code where helpful.
• Only pass --resolve when the user explicitly asks. Never resolve proactively.

Use --json for atomicity (single write, no partial state) and speed (one process). Two ways to feed the JSON:

# Short, single-line bodies — pipe via stdin:
echo '[
  {"body": "overall feedback", "scope": "review"},
  {"path": "session.go", "body": "restructure", "scope": "file"},
  {"file": "src/auth.go", "line": 42, "body": "Missing null check"},
  {"file": "src/auth.go", "line": "50-55", "body": "Extract to helper"},
  {"reply_to": "c_a1b2c3", "body": "Fixed — added null check"},
  {"reply_to": "r_f1e2d3", "body": "Done"}
]' | crit comment --json --author 'Claude Code'

Prefer --file <path> for any multi-paragraph body. Shell-quoted JSON breaks the moment a "body" string contains a raw newline — JSON forbids them, and the shell happily passes them through. Use the Write tool to author the JSON to a temp file, then point crit at it:

# After Write-ing /tmp/replies.json:
crit comment --json --file /tmp/replies.json --author 'Claude Code'

--file - reads stdin (same as omitting the flag).

Per-entry schema:

Scope inference (when scope omitted): has reply_to → reply; no file/path and no line → review-level; path but no line → file-level; file/path + line → line.

crit comment --reply-to c_a1b2c3 --path src/auth.go --author 'Claude Code' 'Fixed the null check'

In --json mode, set the file field on the entry. Review-level IDs (r_…) are globally unique and never need this.

crit comment --plan my-plan-2026-03-23 --reply-to c_a1b2c3 --author 'Claude Code' 'Updated the plan'

crit pull [number|url]                                   # Fetch PR/MR review comments into the review file
crit push [--dry-run] [--event <type>] [-m <msg>] [n]    # Post review comments to a PR/MR
crit pull --forge gitlab 42                              # Force GitLab when auto-detect is ambiguous

Requires gh (GitHub) or glab (GitLab) installed and authenticated. Change number is auto-detected from the current branch when possible. Set "forge" / "gitlab_url" in config for self-managed hosts, or pass --forge.

--event values: comment (default), approve, request-changes. -m adds a review-level body message.

crit share <file> [file...]                          # Upload and print URL
crit share --share-url <url> <file>                  # Target a specific Crit deployment
crit share --qr <file>                               # Also print QR code (terminal only)
crit share --org <slug> <file>                       # Share under an organization
crit share --org <slug> --visibility unlisted <file> # Org share with explicit visibility
crit unpublish [file...]                              # Remove shared review
crit unpublish --share-url <url> [file...]            # Unpublish from a specific deployment

• No server needed — reads files directly from disk. If a review file exists, comments for the shared files are included automatically.
• Always relay the output — copy the URL (and QR if used) into your response. Don't make the user dig through tool output.
• --qr is terminal-only — skip in mobile apps, web chat UIs, or anywhere Unicode block characters won't render correctly.
• --org <slug> shares under an organization. Visibility defaults to organization (members only). Override with --visibility (organization, unlisted, public).
• --share-url selects among configured share_targets (or overrides for one invocation). Required when multiple targets are configured and none is marked default. Empty CRIT_SHARE_URL= disables sharing for the process.
• Unpublish uses the persisted delete token in the review file — no extra args needed unless targeting a non-default deployment with --share-url.