chat-customizations-editor
Skill175 starsChanged 8 months agoMITView on GitHub
Use when working on the Chat Customizations editor — the management UI for agents, skills, instructions, hooks, prompts, MCP servers, and plugins.
5 other projects use a version of this, 4 of them edited.
Adopted by
Most recently taken up by
- microsoft/vscodeedited, first seen Nov 2, 2026
- NeuralInverse/neuralinverseedited, first seen Oct 8, 2026
- posit-dev/positronedited, first seen Oct 8, 2026
- xAmirHamza77/OmniCodeedited, first seen May 21, 2026
- cpkt9762/opencode-vscode-ideword for word, first seen Mar 31, 2026
Other versions5 projects use a version of this.
Word for word · 1
- cpkt9762/opencode-vscode-ide★ 17100% same
Edited · 4
- microsoft/vscode★ 195k72% same
- posit-dev/positron★ 4.3k89% same
- NeuralInverse/neuralinverse★ 22195% same
- xAmirHamza77/OmniCode★ 1295% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- launchSkill
- accessibilitySkill
- add-policySkill
- agent-sessions-layoutSkill
- author-contributionsSkill
- auto-perf-optimizeSkill
- azure-pipelinesSkill
- chat-perfSkill
- component-fixturesSkill
- cpu-profile-analysisSkill
- fix-ci-failuresSkill
- fix-errorsSkill
- heap-snapshot-analysisSkill
- hygieneSkill
- integration-testsSkill
- memory-leak-auditSkill
- sessionsSkill
- tool-rename-deprecationSkill
- unit-testsSkill
- update-screenshotsSkill
- vscode-dev-workbenchSkill
The file
We split this skill into the rules it gives an agent
6 rules. 1 is common, 0 are distinctive, and 5 are very specific to this project.
1
Common
Most of the 4 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 23
When changing harness descriptor interfaces or factory functions, verify both core and sessions registrations compile.
- Very specific: line 46
When adding fields to IExternalCustomizationItem, update all five layers.
- Very specific: line 72
Adding a new tab fixture: Add a variant to the defineThemedFixtureGroup in aiCustomizationManagementEditor.fixture.ts:
- Very specific: line 95
All test data lives in allFiles (prompt-based items) and the mcpWorkspace/UserServers arrays.
- Very specific: line 129
Don't add blocksCi to every fixture — only ones that cover critical layout paths (default view, section with list + footer, narrow …
- Very specific: line 157
After connecting, use snapshot -i to find the "Open Customizations" button (in the Chat panel header), then click it.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Chat Customizations Editor
Split-view management pane for AI customization items across workspace, user, extension, and plugin storage. Supports harness-based filtering (Local, Copilot CLI, Claude).
Spec
src/vs/sessions/AI_CUSTOMIZATIONS.md — always read before making changes, always update after.
Key Folders
| Folder | What |
src/vs/workbench/contrib/chat/common/ | ICustomizationHarnessService, ISectionOverride, IStorageSourceFilter — shared interfaces and filter helpers |
src/vs/workbench/contrib/chat/browser/aiCustomization/ | Management editor, list widgets (prompts, MCP, plugins), harness service registration |
src/vs/sessions/contrib/chat/browser/ | Sessions-window overrides (harness service, workspace service) |
src/vs/sessions/contrib/sessions/browser/ | Sessions tree view counts and toolbar |
When changing harness descriptor interfaces or factory functions, verify both core and sessions registrations compile.
Key Interfaces
IHarnessDescriptor— drives all UI behavior declaratively (hidden sections, button overrides, file filters, agent gating). See spec for full field reference.ISectionOverride— per-section button customization (command invocation, root file creation, type labels, file extensions).IStorageSourceFilter— controls which storage sources and user roots are visible per harness/type.IExternalCustomizationItemProvider/IExternalCustomizationItem— internal interfaces (incustomizationHarnessService.ts) for extension-contributed providers that supply items directly. These mirror the proposed extension API types.
Principle: the UI widgets read everything from the descriptor — no harness-specific conditionals in widget code.
Extension API (chatSessionCustomizationProvider)
The proposed API in src/vscode-dts/vscode.proposed.chatSessionCustomizationProvider.d.ts lets extensions register customization providers. Changes to IExternalCustomizationItem or IExternalCustomizationItemProvider must be kept in sync across the full chain:
| Layer | File | Type |
| Extension API | vscode.proposed.chatSessionCustomizationProvider.d.ts | ChatSessionCustomizationItem |
| IPC DTO | extHost.protocol.ts | IChatSessionCustomizationItemDto |
| ExtHost mapping | extHostChatAgents2.ts | $provideChatSessionCustomizations() |
| MainThread mapping | mainThreadChatAgents2.ts | provideChatSessionCustomizations callback |
| Internal interface | customizationHarnessService.ts | IExternalCustomizationItem |
When adding fields to IExternalCustomizationItem, update all five layers. The proposed API .d.ts is additive-only (new optional fields are backward-compatible and do not require a version bump).
Testing
Component explorer fixtures (see component-fixtures skill): aiCustomizationListWidget.fixture.ts, aiCustomizationManagementEditor.fixture.ts under src/vs/workbench/test/browser/componentFixtures/.
Screenshotting specific tabs
The management editor fixture supports a selectedSection option to render any tab. Each tab has Dark/Light variants auto-generated by defineThemedFixtureGroup.
Available fixture IDs (use with mcp_component-exp_screenshot):
| Fixture ID pattern | Tab shown |
chat/aiCustomizations/aiCustomizationManagementEditor/AgentsTab/{Dark,Light} | Agents |
chat/aiCustomizations/aiCustomizationManagementEditor/SkillsTab/{Dark,Light} | Skills |
chat/aiCustomizations/aiCustomizationManagementEditor/InstructionsTab/{Dark,Light} | Instructions |
chat/aiCustomizations/aiCustomizationManagementEditor/HooksTab/{Dark,Light} | Hooks |
chat/aiCustomizations/aiCustomizationManagementEditor/PromptsTab/{Dark,Light} | Prompts |
chat/aiCustomizations/aiCustomizationManagementEditor/McpServersTab/{Dark,Light} | MCP Servers |
chat/aiCustomizations/aiCustomizationManagementEditor/PluginsTab/{Dark,Light} | Plugins |
chat/aiCustomizations/aiCustomizationManagementEditor/LocalHarness/{Dark,Light} | Default (Agents, Local harness) |
chat/aiCustomizations/aiCustomizationManagementEditor/CliHarness/{Dark,Light} | Default (Agents, CLI harness) |
chat/aiCustomizations/aiCustomizationManagementEditor/ClaudeHarness/{Dark,Light} | Default (Agents, Claude harness) |
chat/aiCustomizations/aiCustomizationManagementEditor/Sessions/{Dark,Light} | Sessions window variant |
Adding a new tab fixture: Add a variant to the defineThemedFixtureGroup in aiCustomizationManagementEditor.fixture.ts:
MyNewTab: defineComponentFixture({
labels: { kind: 'screenshot' },
render: ctx => renderEditor(ctx, {
harness: CustomizationHarness.VSCode,
selectedSection: AICustomizationManagementSection.MySection,
}),
}),The selectedSection calls editor.selectSectionById() after setInput, which navigates to the specified tab and re-layouts.
Populating test data
Each customization type requires its own mock path in createMockPromptsService:
- Agents —
getCustomAgents()returns agent objects - Skills —
findAgentSkills()returnsIAgentSkill[] - Prompts —
getPromptSlashCommands()returnsIChatPromptSlashCommand[] - Instructions/Hooks —
listPromptFiles()filtered byPromptsType - MCP Servers —
mcpWorkspaceServers/mcpUserServersarrays passed toIMcpWorkbenchServicemock - Plugins —
IPluginMarketplaceService.installedPluginsandIAgentPluginService.pluginsobservables
All test data lives in allFiles (prompt-based items) and the mcpWorkspace/UserServers arrays. Add enough items per category (8+) to invoke scrolling.
Exercising built-in grouping
The list widget regroups items from the default chat extension under a "Built-in" header. Three things must be in place for fixtures to exercise this:
- Include
BUILTIN_STORAGEin the harness descriptor's visible sources - Mock
IProductService.defaultChatAgent.chatExtensionId(e.g.,'GitHub.copilot-chat') - Give mock items extension provenance via
extensionId/extensionDisplayNamematching that ID
Without all three, built-in regrouping silently doesn't run and the fixture only shows flat lists.
Editor contribution service mocks
The management editor embeds a CodeEditorWidget. Electron-side editor contributions (e.g., AgentFeedbackEditorWidgetContribution) are instantiated automatically and crash if their injected services aren't registered. The fixture must mock at minimum:
IAgentFeedbackService— needsonDidChangeFeedback,onDidChangeNavigationasEvent.NoneICodeReviewService— needsgetReviewState()/getPRReviewState()returning idle observablesIChatEditingService— needseditingSessionsObsas empty observableIAgentSessionsService— needsmodel.sessionsas empty array
These are cross-layer imports from vs/sessions/ — use // eslint-disable-next-line local/code-import-patterns on the import lines.
CI regression gates
Key fixtures have blocksCi: true in their labels. The screenshot-test.yml GitHub Action captures screenshots on every PR to main and fails the CI status check if any blocks-ci-labeled fixture's screenshot changes. This catches layout regressions automatically.
Currently gated fixtures: LocalHarness, McpServersTab, McpServersTabNarrow, AgentsTabNarrow. When adding a new section or layout-critical fixture, add blocksCi: true:
MyFixture: defineComponentFixture({
labels: { kind: 'screenshot', blocksCi: true },
render: ctx => renderEditor(ctx, { ... }),
}),Don't add blocksCi to every fixture — only ones that cover critical layout paths (default view, section with list + footer, narrow viewport). Too many gated fixtures creates noisy CI.
Screenshot stability
Scrollbar fade transitions cause screenshot instability — the scrollbar shifts from visible to invisible fade class ~2 seconds after a programmatic scroll. After calling revealLastItem() or any scroll action, wait for the transition to complete before the fixture's render promise resolves:
await new Promise(resolve => setTimeout(resolve, 2400));
// Then optionally poll until .scrollbar.vertical loses the 'visible' classRunning unit tests
./scripts/test.sh --grep "applyStorageSourceFilter|customizationCounts"
npm run compile-check-ts-native && npm run valid-layers-checkSee the sessions skill for sessions-window specific guidance.
Debugging Layout in the Real Product
Component fixtures use mock data and a fixed container size. Layout bugs caused by reflow timing, real data shapes, or narrow window sizes often don't reproduce in fixtures. When a user reports a broken layout, debug in the live Code OSS product.
For launching Code OSS with CDP and connecting agent-browser, see the launch skill. Use --user-data-dir /tmp/code-oss-debug to avoid colliding with an already-running instance from another worktree.
Navigating to the customizations editor
After connecting, use snapshot -i to find the "Open Customizations" button (in the Chat panel header), then click it. To switch sections, use eval with a DOM click since sidebar items aren't interactive refs:
npx agent-browser eval "const items = [...document.querySelectorAll('.section-list-item')]; \
items.find(el => el.textContent?.includes('MCP'))?.click();"Inspecting widget layout
agent-browser eval doesn't always print return values. Use document.title as a return channel:
npx agent-browser eval "const w = document.querySelector('.mcp-list-widget'); \
const lc = w?.querySelector('.mcp-list-container'); \
const rows = lc?.querySelectorAll('.monaco-list-row'); \
document.title = 'DBG:rows=' + (rows?.length ?? -1) \
+ ',listH=' + (lc?.offsetHeight ?? -1) \
+ ',seStH=' + (lc?.querySelector('.monaco-scrollable-element')?.style?.height ?? '') \
+ ',wH=' + (w?.offsetHeight ?? -1);"
npx agent-browser eval "document.title" 2>&1Key diagnostics:
rows— fewer than expected meanslist.layout()never received the correct viewport height.seStH— empty means the list was never properly laid out.listHvswH— list container height should be widget height minus search bar minus footer.
Common layout issues
| Symptom | Root cause | Fix pattern |
| List shows 0-1 rows in a tall container | layout() bailed out because offsetHeight returned 0 during display:none → visible transition | Defer layout via DOM.getWindow(this.element).requestAnimationFrame(...) |
| Badge or row content clips at right edge | Widget container missing overflow: hidden | Add overflow: hidden to the widget's CSS class |
| Items visible in fixture but not in product | Fixture uses many mock items; real product has few | Add fixture variants with fewer items or narrower dimensions (width/height options) |
Fixture vs real product gaps
Fixtures render at a fixed size (default 900×600) with many mock items. They won't catch:
- Reflow timing — the real product's
display:none → visibletransition may not have reflowed beforelayout()fires - Narrow windows — add narrow fixture variants (e.g.,
width: 550, height: 400) - Real data counts — a user with 1 MCP server sees very different layout than a fixture with 12
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

