robotframework-lint

70 to 100% fewer issues left.

With the LSP and its auto-fix hook, coding agents leave far fewer Robot Framework lint issues. On Haiku and Sonnet that costs about 10 percent more than no lint, and less than the robocop MCP on every model.

4.7Haiku issues left, against 18.5 without lint and 13.2 with the robocop MCP
2.0Sonnet issues left, against 12.0 without lint
0Opus issues left, against 11.0 without lint

Measured 2026-11-14 on one task: write two Robot Framework suites with keywords, then run them. Every run in every arm ended with passing tests and a clean dry run. Issues left = robocop 9.4.0 default findings in the final files. Plugin version c84eb65.

The hook made the difference.

Haiku, 25 runs per arm, default effort. Issues left per run.

LSP v6, shippedother arms

No LSP

18.5

Robocop MCP

13.2

LSP v2

13.0

LSP v4

16.5

LSP v5

16.5

LSP v6

4.7
VersionWhat changedCost / runTurnsIssues left
No LSPBaseline$0.0281618.5
Robocop MCPLint as MCP tools$0.0362713.2
LSP v2Deprecations shown as warnings$0.03620.713.0
LSP v4Grouped findings, fix commands$0.03421.416.5
LSP v5Ungrouped, more fix commands$0.03319.816.5
LSP v6Auto-fix hook after edits$0.03418.94.7

In v4 and v5 agents read the fix commands but never ran one, in 56 runs. The v6 hook applies the same fixes without spending a turn.

Cheaper than the MCP on every model.

3 runs per arm, effort medium. A small sample: read these as direction, not exact figures.

LSP v6no LSP, robocop MCP

Haiku

none
17.3 | $0.030
MCP
13.7 | $0.040
LSP
4.7 | $0.033

Sonnet

none
12.0 | $0.171
MCP
2.7 | $0.319
LSP
2.0 | $0.186

Opus

none
11.0 | $0.251
MCP
0 | $0.443
LSP
0 | $0.395
ModelCost noneCost MCPCost LSPTurns noneTurns MCPTurns LSP
Haiku$0.030$0.040$0.033192621
Sonnet$0.171$0.319$0.1868.72711.7
Opus$0.251$0.443$0.3951118.317

Bars show issues left; the figure after the bar is issues left and cost per run. On Sonnet the LSP cost 42% less than the MCP. On Opus it cost 58% more than no lint.

Edit, fix, report.

  1. Agent edits

    The agent writes or edits a .robot or .resource file.

    PostToolUse
  2. Auto-fix hook

    Robocop's safe fixes run on the file. It prints nothing.

    didChange
  3. LSP lints

    Robocop defaults plus the RFL rules, warnings and up, at most 20.

    short lines
  4. Diagnostics pushed

    One line per finding, 120 characters at most, with a fix hint.

    next turn
  5. Agent fixes the rest

    Only what robocop cannot fix reaches it, such as long keywords.

Before you trust it on your repo.

  • Run the same task on your own suites. One task is one data point.
  • Confirm the hook runs: claude --debug shows PostToolUse with robotframework-lint-autofix and status 0.
  • Count leftover issues with robocop check on the final files, not from the chat.

Harness, task and raw results | Agent setup guide