@workser/cli 0.6.15 → 0.6.16
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/dist/index.js +254 -737
- package/package.json +1 -1
- package/skills/workser/SKILL.md +0 -1
- package/skills/workser/reference/agent-cloud.md +21 -0
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@workser/cli",
|
|
3
|
-
"version": "0.6.
|
|
3
|
+
"version": "0.6.16",
|
|
4
4
|
"description": "Workser CLI — give your local AI agent native DevOps & infrastructure on Workser. The agent runs `workser …` to provision, deploy, and manage real apps.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"type": "module",
|
package/skills/workser/SKILL.md
CHANGED
|
@@ -30,7 +30,6 @@ load.
|
|
|
30
30
|
| Build an automation, or use Gmail/Slack/Stripe/Sheets | `workflow …`, `app …` | `workser help automation` |
|
|
31
31
|
| Generate an image | `image …` | `workser help images` |
|
|
32
32
|
| Hand a subtask to another agent | `agent …` | `workser help roles` |
|
|
33
|
-
| Ship an AI agent inside the user's app | `agent-cloud …` | `workser help agent-cloud` |
|
|
34
33
|
| Recall across conversations; leave this task's team a fact | `memory …`, `workser note` | `workser help memory` |
|
|
35
34
|
| Record finished output, or ask the user a question | `artifact …`, `ask` | `workser help deliverables` |
|
|
36
35
|
| Control this machine — files, shell, screen, browser | `tool …` | `workser help computer-use` |
|
|
@@ -79,6 +79,27 @@ workser agent-cloud machines # video, data analysis, design, ...
|
|
|
79
79
|
A model marked "needs your own key" will make `publish` FAIL unless a matching
|
|
80
80
|
secret is stored first. Add the key with `add <id> secret` before setting it.
|
|
81
81
|
|
|
82
|
+
## Agents need a paid plan — the trial does not include them
|
|
83
|
+
|
|
84
|
+
`create` and `run` both refuse with **402** on a free or trialling
|
|
85
|
+
organisation. That is a rule, not a fault: every run buys model tokens and
|
|
86
|
+
holds a machine, so it costs real money the moment it happens.
|
|
87
|
+
|
|
88
|
+
**When you hit it, hand the plan over — do not just describe it.** Workser
|
|
89
|
+
files the refusal on the conversation as a step and an artifact the user can
|
|
90
|
+
click, so the person you are helping gets something actionable rather than a
|
|
91
|
+
paragraph. Say plainly what you were doing, that agents need a plan, and stop.
|
|
92
|
+
|
|
93
|
+
Do NOT:
|
|
94
|
+
|
|
95
|
+
- retry the call, or try a different agent — the answer is the same
|
|
96
|
+
- try to work around it by running the job yourself as a coding agent; that is
|
|
97
|
+
a different product and it will not be there when the user closes the window
|
|
98
|
+
- guess at prices, discounts or trial extensions
|
|
99
|
+
|
|
100
|
+
If the user asks how much: it is per minute of run time plus the model, and the
|
|
101
|
+
plan page has the current figures. You do not have them.
|
|
102
|
+
|
|
82
103
|
## When to reach for this
|
|
83
104
|
|
|
84
105
|
When the user describes a job that **keeps happening** and needs judgement:
|