Repository navigation
Add repo-tuned Warden review skills - #2939
Merged
Merged
Conversation
Co-Authored-By: Amir Mujacic <amir.mujacic@sentry.io>
Contributor
|
Co-Authored-By: Amir Mujacic <amir.mujacic@sentry.io>
Co-Authored-By: Amir Mujacic <amir.mujacic@sentry.io>
Co-Authored-By: Amir Mujacic <amir.mujacic@sentry.io>
The org Warden workflow does not start on ready_for_review, so this action never matches. Co-Authored-By: Amir Mujacic <amir.mujacic@sentry.io>
Match getsentry/sentry: drop draft = false so skills also run on draft PRs. Co-Authored-By: Amir Mujacic <amir.mujacic@sentry.io>
bitsandfoxes
approved these changes
Nov 16, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds two repo-tuned Warden skills and a
warden.toml, so Warden can take over what Cursor Bugbot catches in this repo. Today Warden only runs the org-levelsecurity-reviewhere, and that skill covered none of Bugbot's fixed findings.#skip-changelog
What Bugbot found (last 6 months)
Scope: merged PRs from 2026-05-11 to 2026-11-11. That is 194 merged PRs, 100 of them not dependency-bot PRs. Bugbot left 94 inline findings on 42 PRs.
How the outcomes were decided:
CI/build is 43% of the fixed findings here, much more than the cross-repo average. So it gets its own skill.
Recurring fixed patterns:
GetSubtargetcalled on non-standalone builds,arm64vsARM64, Switch 2,nameof(target)(#2858, #2882, #2894, #2834).Experimental.*vs top-level mix-ups (#2749, #2687).wait-for-artifactpolls for but nothing produces anymore, missingactions: read, Xcode or simulator pins that the image no longer has (#2701, #2665, #2871).The dismissed findings became "What not to report" rules in the skills:
-insemantics (#2805)Skills
unity-sdk-reviewcoverssrc/**/*.cs,package-devC#/ObjC/C/ProGuard sources,*.asmdef, andtest/**/*.cs, but nottest/Scripts.Integration.Test. It is tuned to the patterns above and also checks threading/GPU readback, batch-mode assumptions, and tests that hide regressions. It encodes facts that change a verdict:src/is built once against Unity 2021.3, so#if UNITY_*never applies there; iOS and macOS share the Cocoa code; the Warden checkout has no submodules. Bridge-parity and Editor build-pipeline details are inreferences/, which the skill reads only when a hunk needs them.unity-ci-reviewcovers.github/**,scripts/**,*.ps1/*.sh, MSBuild props/targets/csproj,build/**, package metadata,test/Scripts.*, and the sampleAssets/Editorbuild scripts. PowerShell details are inreferences/powershell.md.The two skills' paths do not overlap, so no hunk is reviewed twice. Out of 94 Bugbot findings, 84 fall in scope (57 of 61 fixed). Not covered:
CHANGELOG.md, sampleProjectSettings.assetandSentryOptions.assetfiles, and one sample script.The built-in
code-reviewis not enabled. It is generic: its references cover JS/TS, Python, and workflows, not C#, Unity, IL2CPP, or PowerShell. Running it next to these skills would review every hunk twice on a high-effort model. The repo skills keep its "bugs only, prove it" bar and its severity scale.Config
security-reviewcomes from the org base and is not redeclared. Warden ignores a repo skill with the same name as a base skill.incrementalAppare inherited from the base config, with no overrides.reportOn,failOn, orignorePaths. SeeinheritRepoLayerDefaultsandresolveLayeredSkillConfigsinpackages/warden/src/config/loader.ts, and the loader test "inherits base execution defaults without inheriting base policy defaults". Sowarden.tomlrepeats the org policy values in[defaults]:reportOnlow,failOnoff,failCheckfalse,requestChangesfalse. Findings of every severity are posted as comments and nothing blocks a PR. Low is on so Warden can be compared fairly with Bugbot, which got low-severity findings fixed too. The baseignorePathsstill does not apply, which is why the test-focused rules can seetest/**.incremental = trueon both skills, with triggers onopened/synchronize/reopened.Cost
code-reviewprompt (7.5k).lowlevel (a real bug with a small blast radius) and exclude style, dead code, and suspicion, so reporting at low does not turn into a lint pass.Validation
pnpm install && pnpm build, v0.53.0).warden.tomlwithloadLayeredWardenConfigandresolveLayeredSkillConfigs, and resolved each skill withresolveSkillAsync..agents/skills/.grok-4.5, effort high, runtime pi, andincrementalAppsentry-warden.matchGlob, the skills match 239 and 134 tracked files with zero overlap.Open questions
samples/assets (serialized options,ProjectSettingsteam IDs) be in scope? One fixed and three ignored findings came from there.draft, so draft PRs are reviewed too, the same as getsentry/sentry. Each push to a draft costs a review run;incremental = truekeeps it to what changed since the last run.via amir.
--
View Session [Sentry]