Ruff
51,351Extremely fast Python linter and formatter, written in Rust.
Activity band details
Activity band A to F: a bin of a score that adds GitHub stars (log scale), a push to the upstream repository in the 12 months before `as_of`, the number of declared integration surfaces and, where the catalogue records them, citing papers and benchmark evaluations. It measures popularity and activity. It is not a level of evidence: no band means a paper cites the tool or that it was measured. Recency is judged as of 2026-11-22.
Computed band: A
(raw score 7.38).
Shown band: A
.
Facets:
documented_in=0evaluated_on=2integration_surfaces=1.5paper_citations=0recent_push=2stars=1.88
Source of truth: pipeline/maturity/score.py
Measured on SAICA-Bench in this configuration
Each row is one run of Ruff, set up by us as its run card says, on one labelled set of faulty and clean samples (how we test). It says what that configuration flagged on that set, not how good Ruff is in general: another model, another input or the tool's own defaults could score differently. J = TPR - FPR, on the answers that carry a verdict. 0% is chance, 100% flags every bad sample and no clean one. J is the sort key within a mode; each row also has false alarms per 100 clean changes and precision at 1%, 5% and 20% prevalence.
| Set | Configuration and run card | J (95% interval) | TPR | FPR | No verdict | Cost per 1,000 reviews |
|---|---|---|---|---|---|---|
|
False 'done' claims
failure mode: Incomplete execution
Real agent output
|
ruff FIX rules (TODO / FIXME / XXX / HACK comments)
Catalog tool · Free program · own check
Rank 9 of 10 ranked rows; no reviewer reaches J 25% on this set.
How this run differs from the tool's defaults
|
+0.5%
−0.2% to +1.5%
|
0.5% | 0.0% | 0 | $0 |
|
Logic error
Model-written code, not agent output
|
ruff (pyflakes + bugbear rules)
Catalog tool · Free program · own check · outside design scope
Not ranked: outside the tool's design scope: a linter looks for lint findings, not for wrong results; shown as a floor.
How this run differs from the tool's defaults
|
−3.1%
−5.4% to −0.9%
|
4.3% | 7.4% | 0 | $0 |
|
Fabrication
Failure planted on purpose
|
ruff
Catalog tool · Free program · own check
Rank 14 of 15 ranked rows.
How this run differs from the tool's defaults
|
+54.0%
+47.3% to +60.2%
|
57.5% | 3.5% | 0 | $0 |
|
Obsolescence
Failure planted on purpose
|
ruff NumPy rules (NPY)
Catalog tool · Free program · own check
Rank 8 of 9 ranked rows.
How this run differs from the tool's defaults
|
+7.7%
0.0% to +17.0%
|
7.7% | 0.0% | 0 | $0 |
|
Obsolescence
Failure planted on purpose
|
ruff pyupgrade rules (UP)
Catalog tool · Free program · own check
Rank 9 of 9 ranked rows.
How this run differs from the tool's defaults
|
+1.3%
−4.4% to +7.2%
|
7.1% | 5.8% | 0 | $0 |
An answer with no verdict (failed call, blocked request, text cut by the token budget, no verdict in the text) is unreadable: it is left out of the rates and counted beside them, per label. “~” marks an estimated cost. SAICA-Bench results v2.0.0, built 2026-11-22.
Description
Ruff is a Rust-based linter and formatter for Python that consolidates the rule sets of flake8, isort, pydocstyle, pyupgrade, and many other legacy tools into a single binary that runs orders of magnitude faster. It runs from the CLI, in pre-commit, in CI, and as a language-server inside editors, surfacing logic errors, dead code, import ordering issues, and stylistic drift before review. Configuration lives in pyproject.toml [tool.ruff], which is exactly the surface the audit detector now parses.
Why it's included
Occupies detection × post_generation × fully_autonomous in the Python lane. Tag basis (2026-11-20 tag audit, research/fm_tag_audit/final_table.csv): logic_error from the flake8-bugbear and pyflakes rule families; fabrication from undefined-name (F821); obsolescence from the deprecated-import and pyupgrade rules; security_vulnerability from the flake8-bandit (S) rules; incomplete_execution from the TODO / FIXME rules. The audit removed scope_creep: a linter has no notion of task scope. Mature workhorse rather than novel research, but missing it leaves the audit detector blind to the most common pyproject.toml [tool.ruff] configuration in modern Python repos (e.g. openai-python).
Security notes
Standard dev-tool security posture; runs offline against local source with no network calls. Rule definitions ship with the binary, so supply-chain risk is bounded to the pinned Ruff version itself.
Addresses failure modes
These tags are the catalog's claim about what Ruff is built to catch or prevent. A tag is not a test result. The rows under Measured on SAICA-Bench are the evidence, for the sets and the configuration we ran. Not measured here: Security vulnerability.
- Logic error — Correct API use, incorrect logic.
- Fabrication — Generating reference to non-existent APIs, packages, or symbols.
- Incomplete execution — Agent claims completion while subtasks are skipped, stubbed, or silently dropped.
- Obsolescence — Using deprecated APIs, retired packages, or outdated library versions — often because the model's training data pre-dates current releases.
- Security vulnerability — Insecure patterns, injection flaws, weak cryptography, secret leakage.