code-review-and-quality: worth installing? Measured results

Measured results for code-review-and-quality (addyosmani/agent-skills) from Driftproof, one row per receipt, in plain words.

Skill skills/code-review-and-quality in addyosmani/agent-skills.

One row per receipt. No figure on this page combines two rows.

Measured by: Measured by Driftproof, Report 014
Model: Claude Haiku 4.5 (claude-haiku-4-5-20251001)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-10-07
Tasks and runs: 1 task; 4 runs with the skill and 4 without
Result: Too few answers to tell: 0.566 with the skill and 0.547 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: no draw count at these spreads (case severity-labeled-findings: the two arms' spreads sum to 0.300, at or above the 0.05 floor).
Tokens: 18950 input and 1167 output tokens per call with the skill; 14097 and 1135 without. 0.0248 US dollars per call with the skill, 0.0198 without, at list price from the receipt's price snapshot.
Freshness: Measured on Haiku 4.5. The registry lists no haiku model released after this run, as of the build date.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-haiku-4-5-20251001-2026-10-07.json

Measured by: Measured by Driftproof, Report 014
Model: Claude Haiku 4.5 (claude-haiku-4-5-20251001)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-10-07
Tasks and runs: 1 task; 6 runs with the skill and 7 without
Result: Too few answers to tell: 0.628 with the skill and 0.540 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: no draw count at these spreads (case severity-labeled-findings: the two arms' spreads sum to 0.284, at or above the 0.05 floor).
Tokens: 18950 input and 1317 output tokens per call with the skill; 14097 and 1201 without. 0.0255 US dollars per call with the skill, 0.0201 without, at list price from the receipt's price snapshot.
Freshness: Measured on Haiku 4.5. The registry lists no haiku model released after this run, as of the build date.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-haiku-4-5-20251001-2026-10-07.json

Measured by: Measured by Driftproof, Report 014
Model: Claude Haiku 5.5 (claude-haiku-5-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-10-07
Tasks and runs: 1 task; 10 runs with the skill and 3 without
Result: Too few answers to tell: 0.770 with the skill and 0.823 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: no draw count at these spreads (case severity-labeled-findings: the two arms' spreads sum to 0.189, at or above the 0.05 floor).
Tokens: 26813 input and 2355 output tokens per call with the skill; 19838 and 2360 without. 0.0039 US dollars per call with the skill, 0.0032 without, at list price from the receipt's price snapshot.
Freshness: Measured on claude-haiku-5-5. Freshness unknown: the model is not in the registry.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-haiku-5-5-2026-10-07.json

Measured by: Measured by Driftproof, Report 014
Model: Claude Haiku 4.5 (claude-haiku-4-5-20251001)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-10-07
Tasks and runs: 1 task; 4 runs with the skill and 3 without
Result: The skill clearly helped: 0.677 with it and 0.339 without, on 1 test task.
Tokens: 18950 input and 1430 output tokens per call with the skill; 14097 and 1224 without. 0.0261 US dollars per call with the skill, 0.0202 without, at list price from the receipt's price snapshot.
Freshness: Measured on Haiku 4.5. The registry lists no haiku model released after this run, as of the build date.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-haiku-4-5-20251001-2026-10-07.json

Measured by: Measured by Driftproof, Report 014
Model: Claude Haiku 5.5 (claude-haiku-5-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-10-07
Tasks and runs: 1 task; 4 runs with the skill and 4 without
Result: Too few answers to tell: 0.861 with the skill and 0.813 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: no draw count at these spreads (case severity-labeled-findings: the two arms' spreads sum to 0.144, at or above the 0.05 floor).
Tokens: 26813 input and 2539 output tokens per call with the skill; 19838 and 2194 without. 0.0040 US dollars per call with the skill, 0.0031 without, at list price from the receipt's price snapshot.
Freshness: Measured on claude-haiku-5-5. Freshness unknown: the model is not in the registry.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-haiku-5-5-2026-10-07.json

Measured by: Measured by Driftproof, Report 014
Model: Claude Haiku 5.5 (claude-haiku-5-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-10-07
Tasks and runs: 1 task; 3 runs with the skill and 4 without
Result: The skill clearly helped: 0.891 with it and 0.821 without, on 1 test task.
Tokens: 26813 input and 2487 output tokens per call with the skill; 19838 and 2461 without. 0.0039 US dollars per call with the skill, 0.0032 without, at list price from the receipt's price snapshot.
Freshness: Measured on claude-haiku-5-5. Freshness unknown: the model is not in the registry.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-haiku-5-5-2026-10-07.json

Measured by: Measured by Driftproof, Report 013
Model: Claude Opus 5.5 (claude-opus-5-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-29
Tasks and runs: 1 task; 3 runs with the skill and 5 without
Result: Too few answers to tell: 0.903 with the skill and 0.713 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: no draw count at these spreads (case severity-labeled-findings: the two arms' spreads sum to 0.226, at or above the 0.05 floor).
Tokens: 19712 input and 1826 output tokens per call with the skill; 12737 and 1514 without. 0.1154 US dollars per call with the skill, 0.0812 without, at list price from the receipt's price snapshot.
Freshness: Measured on Opus 5.5. The registry lists no opus model released after this run, as of the build date.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-opus-5-5-2026-09-29.json

Measured by: Measured by Driftproof, Report 013
Model: Claude Sonnet 5 (claude-sonnet-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-29
Tasks and runs: 1 task; 4 runs with the skill and 6 without
Result: Too few answers to tell: 0.657 with the skill and 0.573 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: no draw count at these spreads (case severity-labeled-findings: the two arms' spreads sum to 0.433, at or above the 0.05 floor).
Tokens: 26134 input and 1055 output tokens per call with the skill; 19159 and 988 without. 0.0628 US dollars per call with the skill, 0.0482 without, at list price from the receipt's price snapshot.
Freshness: Measured on Sonnet 5. The registry lists no sonnet model released after this run, as of the build date.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-sonnet-5-2026-09-29.json

Measured by: Measured by Driftproof, Report 013
Model: Claude Sonnet 5.5 (claude-sonnet-5-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-29
Tasks and runs: 1 task; 3 runs with the skill and 3 without
Result: Too few answers to tell: 0.896 with the skill and 0.861 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: 6 draws per arm (case severity-labeled-findings), with the spreads held.
Tokens: 19716 input and 1398 output tokens per call with the skill; 12741 and 1319 without. 0.0534 US dollars per call with the skill, 0.0387 without, at list price from the receipt's price snapshot.
Freshness: Measured on claude-sonnet-5-5. Freshness unknown: the model is not in the registry.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-sonnet-5-5-2026-09-29.json

Measured by: Measured by Driftproof, Report 013
Model: Claude Opus 5.5 (claude-opus-5-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-29
Tasks and runs: 1 task; 3 runs with the skill and 3 without
Result: Too few answers to tell: 0.894 with the skill and 0.857 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: 132 draws per arm (case severity-labeled-findings), with the spreads held.
Tokens: 19712 input and 1580 output tokens per call with the skill; 12737 and 1526 without. 0.1104 US dollars per call with the skill, 0.0815 without, at list price from the receipt's price snapshot.
Freshness: Measured on Opus 5.5. The registry lists no opus model released after this run, as of the build date.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-opus-5-5-2026-09-29.json

Measured by: Measured by Driftproof, Report 013
Model: Claude Sonnet 5 (claude-sonnet-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-29
Tasks and runs: 1 task; 3 runs with the skill and 3 without
Result: The skill clearly helped: 0.881 with it and 0.674 without, on 1 test task.
Tokens: 26134 input and 1007 output tokens per call with the skill; 19159 and 1017 without. 0.0623 US dollars per call with the skill, 0.0485 without, at list price from the receipt's price snapshot.
Freshness: Measured on Sonnet 5. The registry lists no sonnet model released after this run, as of the build date.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-sonnet-5-2026-09-29.json

Measured by: Measured by Driftproof, Report 013
Model: Claude Sonnet 5.5 (claude-sonnet-5-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-29
Tasks and runs: 1 task; 3 runs with the skill and 3 without
Result: Too few answers to tell: 0.900 with the skill and 0.849 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: no draw count at these spreads (case severity-labeled-findings: the two arms' spreads sum to 0.056, at or above the 0.05 floor).
Tokens: 19716 input and 1544 output tokens per call with the skill; 12741 and 1371 without. 0.0549 US dollars per call with the skill, 0.0392 without, at list price from the receipt's price snapshot.
Freshness: Measured on claude-sonnet-5-5. Freshness unknown: the model is not in the registry.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-sonnet-5-5-2026-09-29.json

Measured by: Measured by Driftproof, Report 013
Model: Claude Opus 5.5 (claude-opus-5-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-29
Tasks and runs: 1 task; 3 runs with the skill and 4 without
Result: Too few answers to tell: 0.907 with the skill and 0.831 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: no draw count at these spreads (case severity-labeled-findings: the two arms' spreads sum to 0.080, at or above the 0.05 floor).
Tokens: 19712 input and 1963 output tokens per call with the skill; 12737 and 1466 without. 0.1181 US dollars per call with the skill, 0.0803 without, at list price from the receipt's price snapshot.
Freshness: Measured on Opus 5.5. The registry lists no opus model released after this run, as of the build date.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-opus-5-5-2026-09-29.json

Measured by: Measured by Driftproof, Report 013
Model: Claude Sonnet 5 (claude-sonnet-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-29
Tasks and runs: 1 task; 3 runs with the skill and 4 without
Result: The skill clearly helped: 0.880 with it and 0.578 without, on 1 test task.
Tokens: 26134 input and 807 output tokens per call with the skill; 19159 and 1041 without. 0.0603 US dollars per call with the skill, 0.0487 without, at list price from the receipt's price snapshot.
Freshness: Measured on Sonnet 5. The registry lists no sonnet model released after this run, as of the build date.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-sonnet-5-2026-09-29.json

Measured by: Measured by Driftproof, Report 013
Model: Claude Sonnet 5.5 (claude-sonnet-5-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-29
Tasks and runs: 1 task; 3 runs with the skill and 3 without
Result: Too few answers to tell: 0.887 with the skill and 0.878 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: no draw count at these spreads (case severity-labeled-findings: the two arms' spreads sum to 0.052, at or above the 0.05 floor).
Tokens: 19716 input and 1379 output tokens per call with the skill; 12741 and 1359 without. 0.0532 US dollars per call with the skill, 0.0391 without, at list price from the receipt's price snapshot.
Freshness: Measured on claude-sonnet-5-5. Freshness unknown: the model is not in the registry.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-sonnet-5-5-2026-09-29.json

Measured by: Measured by Driftproof, Report 011
Model: Claude Opus 5 (claude-opus-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-23
Tasks and runs: 1 task; 3 runs with the skill and 3 without
Result: Too few answers to tell: 0.901 with the skill and 0.862 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: 9 draws per arm (case severity-labeled-findings), with the spreads held.
Tokens: 11646 input and 3092 output tokens per call with the skill; 4671 and 2585 without. 0.1355 US dollars per call with the skill, 0.0880 without, at list price from the receipt's price snapshot.
Freshness: Measured on Opus 5. The registry lists no opus model released after this run, as of the build date.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-opus-5-2026-09-23.json

Measured by: Measured by Driftproof, Report 011
Model: Claude Opus 5.5 (claude-opus-5-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-23
Tasks and runs: 1 task; 3 runs with the skill and 4 without
Result: Too few answers to tell: 0.910 with the skill and 0.680 without, but the scores varied too much to call it. Not enough draws to conclude at this effect floor. Draws needed: no draw count at these spreads (case severity-labeled-findings: the two arms' spreads sum to 0.232, at or above the 0.05 floor).
Tokens: 10646 input and 1912 output tokens per call with the skill; 3671 and 1452 without. 0.0808 US dollars per call with the skill, 0.0437 without, at list price from the receipt's price snapshot.
Freshness: Measured on Opus 5.5. The registry lists no opus model released after this run, as of the build date.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-opus-5-5-2026-09-23.json

Measured by: Measured by Driftproof, Report 009
Model: Claude Opus 5 (claude-opus-5)
Harness: Driftproof runner 0.10.1 on claude-cli
Date: 2026-09-15
Tasks and runs: 1 task; 3 runs with the skill and 4 without
Result: The skill clearly helped: 0.918 with it and 0.783 without, on 1 test task.
Tokens: 9536 input and 2641 output tokens per call with the skill; 2561 and 2065 without. 0.1137 US dollars per call with the skill, 0.0644 without, at list price from the receipt's price snapshot.
Freshness: Measured on Opus 5. Registered opus models released after this run, as of the build date: Opus 5.5.
Skill commit: be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39
Receipt: code-review-and-quality-claude-opus-5-2026-09-15.json

Receipts by Driftproof (driftproofhq/driftproof), licensed Apache-2.0.

Disagree, or want a re-run?

Built on 2026-10-15 from committed receipts.