Update to Bencher

Changed files

Choose a file to see its text changes. Binary or large files show metadata only.

plugin.json →

skills/bencher/mcp.md →

skills/bencher/reference.md →

plugin.json

− removed · + added

--- before
+++ after
@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "bencher",
-  "version": "0.6.13",
+  "version": "0.6.14",
   "description": "Catch performance regressions before they merge",
   "author": {
     "name": "Bencher",
@@ -22,7 +22,7 @@
       "interface": {
         "displayName": "Bencher",
         "shortDescription": "Continuous Benchmarking",
-        "longDescription": "Bencher is a continuous benchmarking platform that helps systems software engineers catch performance regressions before they merge.\n\nHow Bencher Works:\n\n1. Run: Run your benchmarks locally or in CI using the exact same bare metal runners and your favorite benchmarking tools. The `bencher` CLI orchestrates running your benchmarks on bare metal and stores the results.\n2. Track: Track the results of your benchmarks over time. Monitor, query, and graph the results using the Bencher web console based on the source branch, testbed, benchmark, and measure.\n3. Catch: Catch performance regressions locally or in CI using the exact same bare metal hardware. Bencher uses state of the art, customizable analytics to detect performance regressions before they merge.\n\nFor the same reasons that unit tests are run to prevent feature regressions, benchmarks should be run with Bencher to prevent performance regressions. Performance bugs are bugs!",
+        "longDescription": "Bencher is a continuous benchmarking platform that helps software engineers and agents catch performance regressions before they merge.\n\nHow Bencher Works:\n\n1. Run: Run your benchmarks locally, in an agent sandbox, or in CI using the exact same bare metal runners and your favorite benchmarking tools. The `bencher` CLI orchestrates running your benchmarks on bare metal and stores the results.\n2. Track: Track the results of your benchmarks over time. Monitor, query, and graph the results using the Bencher web console based on the source branch, testbed, benchmark, and measure.\n3. Catch: Catch performance regressions locally or in CI using the exact same bare metal hardware. Bencher uses state of the art, customizable analytics to detect performance regressions before they merge.\n\nFor the same reasons that unit tests are run to prevent feature regressions, benchmarks should be run with Bencher to prevent performance regressions. Performance bugs are bugs!",
         "developerName": "Bencher",
         "category": "Developer Tools",
         "capabilities": [],
@@ -69,10 +69,10 @@
               "expected_behavior": "Look up the branch, testbed, benchmark, and measure, then return the Latency value of each run in the last 30 days with its date."
             },
             {
-              "description": "Render a performance plot",
-              "prompt": "Plot the Latency of the bencher::mock_0 benchmark on the main branch and ubuntu-latest testbed of the example project on Bencher over the last 30 days.",
-              "tools_triggered": "list_branches, list_testbeds, list_benchmarks, list_measures, perf_image",
-              "expected_behavior": "Look up the branch, testbed, benchmark, and measure, then show a plot image of the Latency values over the last 30 days."
+              "description": "Describe a performance trend",
+              "prompt": "How has the Latency of the bencher::mock_0 benchmark on the main branch and ubuntu-latest testbed of the example project on Bencher changed over the last 4 weeks?",
+              "tools_triggered": "list_branches, list_testbeds, list_benchmarks, list_measures, query_perf",
+              "expected_behavior": "Look up the branch, testbed, benchmark, and measure, then compare the earliest and latest Latency values in the last 4 weeks and say whether Latency went up or down and by about how much."
             }
           ],
           "negative": [