githits 0.11.4 → 0.12.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/marketplace.json +2 -2
- package/.claude-plugin/plugin.json +1 -1
- package/.codex-plugin/plugin.json +1 -1
- package/.cursor-plugin/plugin.json +1 -1
- package/.plugin/plugin.json +1 -1
- package/AGENTS.md +1 -1
- package/dist/cli.js +58 -38
- package/dist/index.js +1 -1
- package/dist/shared/{chunk-xez3y33q.js → chunk-2d25b2jc.js} +1 -1
- package/dist/shared/{chunk-sbpx9c2c.js → chunk-th921mfc.js} +16 -16
- package/dist/shared/{chunk-0w8sxsqp.js → chunk-wwyf1snx.js} +1 -1
- package/gemini-extension.json +1 -1
- package/package.json +1 -1
- package/plugin.json +1 -1
- package/server.json +2 -2
- package/skills/githits-code/SKILL.md +23 -19
- package/skills/githits-mcp/SKILL.md +8 -8
- package/skills/githits-package/SKILL.md +25 -19
|
@@ -6,12 +6,12 @@
|
|
|
6
6
|
},
|
|
7
7
|
"metadata": {
|
|
8
8
|
"description": "The code context layer for AI coding agents",
|
|
9
|
-
"version": "0.
|
|
9
|
+
"version": "0.12.0"
|
|
10
10
|
},
|
|
11
11
|
"plugins": [
|
|
12
12
|
{
|
|
13
13
|
"name": "githits",
|
|
14
|
-
"version": "0.
|
|
14
|
+
"version": "0.12.0",
|
|
15
15
|
"description": "The code context layer for AI coding agents",
|
|
16
16
|
"author": {
|
|
17
17
|
"name": "GitHits"
|
package/.plugin/plugin.json
CHANGED
package/AGENTS.md
CHANGED
|
@@ -27,7 +27,7 @@ Philosophy: "Create architecture that is performant and easy to test"
|
|
|
27
27
|
- Use dependency injection for external services (REST client, etc.)
|
|
28
28
|
- Do not eagerly validate network/proxy/environment configuration while constructing command dependencies when the command has local-only or no-network paths. Defer validation until the first network operation and add regression tests for malformed env values on local paths.
|
|
29
29
|
- For MCP/agent-facing tools, avoid coupled optional flags and default-true booleans. Design schemas for real agent calls, including empty strings, empty arrays, and explicit `false` values.
|
|
30
|
-
- For MCP tool discovery, treat the tool name plus the first
|
|
30
|
+
- For MCP tool discovery, treat the tool name plus the first description sentence as a standalone selection surface. A verified claude.ai deferred-tool catalog rendered at most 80 characters: a sentence longer than 79 characters appeared as its first 79 plus an ellipsis, while connector descriptions and MCP server instructions did not reach selection. Lead with the natural user question and the tool's distinct job, keep that sentence within 79 characters when it must render whole, and avoid internal periods (including abbreviations, version literals, and filenames) because the observed sentence boundary is otherwise ambiguous. Keep registry counts/lists, argument mechanics, and follow-up routing after it. Also keep the first 80 raw description characters useful for clients that expose a raw prefix. Do not rely on neighboring tools for context. Add first-sentence/first-80 contract tests and run descriptor-only agent evals for description changes.
|
|
31
31
|
- For GraphQL/API-backed tools, treat minimal data fetching as part of the tool contract. Before adding or changing selected fields, compare the query against every consumer (text, verbose, JSON, MCP, CLI, and internal callers), use conditional fields or separate queries for mode-specific data, and add tests that assert the wire variables/selections for compact and detailed modes.
|
|
32
32
|
|
|
33
33
|
See `docs/guidelines/ARCHITECTURAL_GUIDELINES.md` for detailed planning checklist and design principles.
|