githits 0.6.6 → 0.6.7
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 +1 -1
- package/.claude-plugin/plugin.json +1 -1
- package/.plugin/plugin.json +1 -1
- package/README.md +1 -0
- package/dist/cli.js +30 -24
- package/dist/index.js +1 -1
- package/dist/shared/{chunk-ffqa4bpw.js → chunk-4cnb4nss.js} +18 -3
- package/dist/shared/{chunk-qh0kv76d.js → chunk-p09q90sj.js} +1 -1
- package/dist/shared/{chunk-pwfqg90m.js → chunk-xr5k540v.js} +1 -1
- package/gemini-extension.json +1 -1
- package/package.json +1 -1
- package/plugins/claude/.claude-plugin/plugin.json +1 -1
- package/plugins/claude/skills/onboarding/SKILL.md +39 -6
- package/server.json +2 -2
- package/skills/githits-code/SKILL.md +10 -7
- package/skills/githits-code/references/code-and-docs.md +3 -1
- package/skills/githits-onboarding/SKILL.md +54 -10
|
@@ -65,20 +65,43 @@ npx -y githits@latest init --detect-agents --json
|
|
|
65
65
|
|
|
66
66
|
Run detection inline, not in a background terminal. Wait for JSON before continuing.
|
|
67
67
|
|
|
68
|
-
Use the JSON fields to summarize detected tools. `agents[].status` can be `needs_setup`, `already_configured`, `unsupported_project_config`, or `not_detected`. `installableIds`
|
|
68
|
+
Use the JSON fields to summarize detected tools. `agents[].status` describes MCP state and can be `needs_setup`, `already_configured`, `unsupported_project_config`, or `not_detected`. `agents[].guidanceStatus` describes supporting guidance. `installableIds` remains MCP-only; use `actionableIds` for tools needing either MCP setup or requested guidance repair.
|
|
69
|
+
|
|
70
|
+
If `actionableIds` is absent because the installed CLI predates guidance-aware detection, use `installableIds` for MCP setup and do not infer guidance-only repair from missing fields.
|
|
69
71
|
|
|
70
72
|
For project-level setup, do not offer tools with `unsupported_project_config`. Explain only if needed: those detected tools do not have verified project-level MCP support.
|
|
71
73
|
|
|
72
|
-
|
|
74
|
+
Before showing the review, classify the detection result:
|
|
75
|
+
|
|
76
|
+
- If every agent is `not_detected`, explain that no supported coding tool was found and stop before review, installation, or authentication. Tell the user to install or open a supported tool, then rerun detection.
|
|
77
|
+
- In project scope, if no agent is `needs_setup` or `already_configured` and at least one is `unsupported_project_config`, explain that project-level setup is unavailable, offer user-level detection, and stop the project flow before review or authentication.
|
|
78
|
+
- If supported agents are mixed with `unsupported_project_config`, explain the unsupported tools but continue only with supported agents.
|
|
79
|
+
- If no effective actionable IDs remain but at least one supported agent is `already_configured`, continue to the review, skip installation after acknowledgment, and then check authentication.
|
|
80
|
+
|
|
81
|
+
Follow the CLI JSON `instructions` remediation for these states rather than replacing it with generic authentication guidance.
|
|
82
|
+
|
|
83
|
+
3. When setup can proceed, show the install review before asking for tool approval or starting browser authentication, including the already-configured supported-tool case.
|
|
84
|
+
|
|
85
|
+
Tell the user:
|
|
73
86
|
|
|
74
|
-
|
|
87
|
+
- GitHits queries and public package, repository, and documentation targets are sent to GitHits services for processing.
|
|
88
|
+
- Feedback submission is an outbound write that sends feedback data to GitHits services.
|
|
89
|
+
- Installing GitHits does not itself upload the local workspace.
|
|
90
|
+
- After installation, open a new coding-agent session so it loads MCP configuration and any supporting instructions. The terminal and machine do not need to be restarted.
|
|
91
|
+
|
|
92
|
+
Ask the user to acknowledge this review before continuing.
|
|
93
|
+
If the user does not acknowledge it, stop onboarding without installing or starting authentication.
|
|
94
|
+
|
|
95
|
+
4. Recommend the simplest actionable setup choice with structured options.
|
|
96
|
+
|
|
97
|
+
If `actionableIds` is non-empty, use structured choices when available. Do not ask the user to type comma-separated tool IDs unless the current agent interface has no structured choice mechanism. Explain whether each ID needs MCP setup, guidance repair, or both.
|
|
75
98
|
|
|
76
99
|
Ask: `Which tools should I configure?`
|
|
77
100
|
|
|
78
101
|
Options:
|
|
79
102
|
|
|
80
|
-
- `Configure all
|
|
81
|
-
- One selective setup option per
|
|
103
|
+
- `Configure all actionable tools (Recommended)` — the recommended default option; after approval execute `suggestedCommand` exactly so scope and guidance intent are preserved.
|
|
104
|
+
- One selective setup option per actionable tool, using the tool display name and ID.
|
|
82
105
|
|
|
83
106
|
Do not present "configure none" as a normal onboarding choice; if the user does not want any tool configured, pause and clarify whether they want to stop onboarding.
|
|
84
107
|
|
|
@@ -86,7 +109,11 @@ Ask before writing configuration. A good prompt is: `I recommend configuring all
|
|
|
86
109
|
|
|
87
110
|
Only install user-approved IDs. Do not run `init -y` or `init --yes` unless the user explicitly asks to configure every detected tool.
|
|
88
111
|
|
|
89
|
-
|
|
112
|
+
For selective setup, build the matching scoped `--install-agents` command and preserve `--no-guidance` when `guidanceRequested` is `false`. Follow the CLI-emitted verification instruction instead of constructing a separate detect command.
|
|
113
|
+
|
|
114
|
+
If no effective actionable IDs remain and at least one supported tool is already configured, skip installation and continue to authentication only after the user acknowledges the install review.
|
|
115
|
+
|
|
116
|
+
5. Install GitHits MCP and supporting guidance for approved tools using the selected scope.
|
|
90
117
|
|
|
91
118
|
Guidance is installed by default. It adds the `githits-mcp` skill and a short instruction pointer for tools with verified guidance paths. Add `--no-guidance` only when the user explicitly asks for plain MCP without supporting instructions.
|
|
92
119
|
|
|
@@ -104,10 +131,14 @@ npx -y githits@latest init --install-agents <comma-separated-approved-ids> --jso
|
|
|
104
131
|
|
|
105
132
|
Treat `success` and `already_configured` outcomes as usable. Report any `failed` outcome with the tool name and message. For project-level setup, remind the user that project-local MCP files may be committed.
|
|
106
133
|
|
|
107
|
-
|
|
134
|
+
Cursor is configured with the remote MCP at `https://mcp.githits.com`, not a local stdio command. An existing Cursor entry that runs `npx ... githits ... mcp start` is legacy and should become `needs_setup`; installing it migrates the entry to the remote URL.
|
|
135
|
+
|
|
136
|
+
6. Start GitHits sign-in/signup during onboarding.
|
|
108
137
|
|
|
109
138
|
Do not ask whether the user wants to log in. Login creates or connects the GitHits account, so it is part of onboarding. Ask before launching browser OAuth, then run login unless `auth status` already shows an active session.
|
|
110
139
|
|
|
140
|
+
This CLI authentication step applies to local GitHits CLI/stdio integrations. Cursor remote MCP authentication is managed separately by Cursor. If Cursor is the only approved tool, skip local CLI login and continue to the Cursor verification below. For a mixed install, use this CLI login step for the non-Cursor tools, but do not treat it as evidence that Cursor is authenticated.
|
|
141
|
+
|
|
111
142
|
Check auth state:
|
|
112
143
|
|
|
113
144
|
```bash
|
|
@@ -134,7 +165,7 @@ npx -y githits@latest login --no-browser
|
|
|
134
165
|
|
|
135
166
|
With `--no-browser`, surface the printed sign-in URL clearly so the user can open it in a browser. If command output is hidden from the user, relay the URL verbatim. Do not ask them to paste passwords, tokens, cookies, or OAuth codes back into chat.
|
|
136
167
|
|
|
137
|
-
|
|
168
|
+
7. Verify setup after login and installation.
|
|
138
169
|
|
|
139
170
|
Project-level verification:
|
|
140
171
|
|
|
@@ -150,14 +181,27 @@ npx -y githits@latest auth status
|
|
|
150
181
|
npx -y githits@latest init --detect-agents --json
|
|
151
182
|
```
|
|
152
183
|
|
|
153
|
-
Confirm auth is active and selected tools are `already_configured` for the selected scope. If MCP configuration changed, tell the user to open a new agent session in the project or user environment so the tool reloads its MCP
|
|
184
|
+
Confirm auth is active and selected tools are `already_configured` for the selected scope. If MCP configuration or supporting guidance changed, tell the user to open a new coding-agent session in the project or user environment so the tool reloads its MCP configuration and any supporting instructions. The terminal and machine do not need to be restarted.
|
|
185
|
+
|
|
186
|
+
For Cursor, `already_configured` verifies only that the remote URL is present. It does not verify Cursor-managed OAuth or tool discovery. Do not report Cursor as ready based on `githits auth status` or init detection alone.
|
|
187
|
+
|
|
188
|
+
If `cursor-agent` is available, verify Cursor directly:
|
|
189
|
+
|
|
190
|
+
```bash
|
|
191
|
+
cursor-agent mcp list
|
|
192
|
+
cursor-agent mcp list-tools GitHits
|
|
193
|
+
```
|
|
194
|
+
|
|
195
|
+
If Cursor reports that authentication is required, run `cursor-agent mcp login GitHits`, let the user complete browser OAuth, then rerun both verification commands. Do not ask the user to paste OAuth data into chat.
|
|
196
|
+
|
|
197
|
+
Whether or not `cursor-agent` is available, tell the user to open a new Cursor Agent chat after installation. In the Cursor MCP tools UI, confirm that GitHits is enabled, complete its OAuth prompt if shown, and confirm that GitHits tools are listed. If the CLI checks cannot run, require the user's confirmation from that new chat before reporting Cursor ready.
|
|
154
198
|
|
|
155
199
|
## Completion Response
|
|
156
200
|
|
|
157
201
|
Report:
|
|
158
202
|
|
|
159
203
|
- Which tools were configured or already configured.
|
|
160
|
-
- Whether GitHits auth
|
|
204
|
+
- Whether local GitHits CLI auth and Cursor-managed OAuth are active, require browser approval, or could not be verified, keeping those states separate.
|
|
161
205
|
- Whether the user needs to restart/open a new agent session.
|
|
162
206
|
- Any failed tool setup with the exact tool name and error message.
|
|
163
207
|
|