@agent-facets/viper-plans-mcp 1.3.1 → 2.0.0
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/README.md +20 -18
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -46,12 +46,11 @@ Then, in your agent:
|
|
|
46
46
|
|
|
47
47
|
The planning command explores the repository, asks you clarifying questions, and shows you the
|
|
48
48
|
finished plan. You approve it — with or without model-switch pauses — and it is written to disk.
|
|
49
|
+
The agent then asks whether to execute it now.
|
|
49
50
|
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
Execution begins immediately: one TODO per step, in order, with the gates the plan declares.
|
|
51
|
+
Choose **Run now** and execution begins immediately: one TODO per step, in order, with the gates the
|
|
52
|
+
plan declares. Choose **Not now** and the plan stays on disk; run it later with
|
|
53
|
+
`/viper-run <name>`.
|
|
55
54
|
|
|
56
55
|
## The step types
|
|
57
56
|
|
|
@@ -127,11 +126,8 @@ you approve.
|
|
|
127
126
|
The agent reads your auth code and asks what it cannot infer — the limit, the window, whether
|
|
128
127
|
lockout is per-account or per-IP. It then shows you a plan and asks how to save it: keeping the
|
|
129
128
|
`Pause` steps, dropping them, or changing something first. On approval it writes
|
|
130
|
-
`.opencode/plans/login-rate-limit/plan.md` and
|
|
131
|
-
|
|
132
|
-
```text
|
|
133
|
-
/viper-continue
|
|
134
|
-
```
|
|
129
|
+
`.opencode/plans/login-rate-limit/plan.md` and asks whether to execute it now. You choose
|
|
130
|
+
**Run now**.
|
|
135
131
|
|
|
136
132
|
The run starts. `Explore` reads the login handler and the existing middleware. `Propose` then shows
|
|
137
133
|
you the actual approach it found — which middleware to extend, where the counter lives, what happens
|
|
@@ -155,14 +151,20 @@ and tells you, rather than pressing on. When the plan finishes, the agent offers
|
|
|
155
151
|
|
|
156
152
|
## The commands
|
|
157
153
|
|
|
158
|
-
| Command | What it does
|
|
159
|
-
|
|
160
|
-
| `/viper-plan <goal>` | Explores, asks, composes,
|
|
161
|
-
| `/viper-
|
|
162
|
-
|
|
154
|
+
| Command | What it does |
|
|
155
|
+
|------------------------|-------------------------------------------------------------------------------------------|
|
|
156
|
+
| `/viper-plan <goal>` | Explores, asks, composes, and saves the plan once you approve, then offers to run it now. |
|
|
157
|
+
| `/viper-run [name]` | Lists saved plans, lets you pick and review one, then executes it. |
|
|
158
|
+
|
|
159
|
+
Answer **Run now** right after planning to execute the plan without another confirmation. Use
|
|
160
|
+
`/viper-run <name>` for a plan you saved with **Not now**, a plan from an earlier session, or after a
|
|
161
|
+
compaction.
|
|
162
|
+
|
|
163
|
+
### Upgrading from 1.x
|
|
163
164
|
|
|
164
|
-
|
|
165
|
-
|
|
165
|
+
2.0.0 removes `/viper-continue`. `/viper-plan` now offers to execute the plan as soon as it is saved,
|
|
166
|
+
so there is no separate command to run the plan you just created. To run a saved plan later, use
|
|
167
|
+
`/viper-run <name>`.
|
|
166
168
|
|
|
167
169
|
## Why the MCP server
|
|
168
170
|
|
|
@@ -224,7 +226,7 @@ To configure the server yourself instead, point your client at the published pac
|
|
|
224
226
|
"mcp": {
|
|
225
227
|
"viper-plans": {
|
|
226
228
|
"type": "local",
|
|
227
|
-
"command": ["npx", "-y", "@agent-facets/viper-plans-mcp@
|
|
229
|
+
"command": ["npx", "-y", "@agent-facets/viper-plans-mcp@2.0.0"]
|
|
228
230
|
}
|
|
229
231
|
}
|
|
230
232
|
}
|