@sellable/install 0.1.300 → 0.1.301

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/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@sellable/install",
3
- "version": "0.1.300",
3
+ "version": "0.1.301",
4
4
  "type": "module",
5
5
  "description": "One-command installer for Sellable MCP in Claude Code and Codex",
6
6
  "bin": {
@@ -0,0 +1,84 @@
1
+ ---
2
+ name: refill-sends-evergreen
3
+ description: Plan evergreen waterfall send refill work through the Phase 85 dry-run workflow.
4
+ visibility: public
5
+ allowed-tools:
6
+ - mcp__sellable__refill_sends_evergreen
7
+ - mcp__sellable__get_evergreen_refill_plan
8
+ - mcp__sellable__get_subskill_prompt
9
+ - mcp__sellable__get_subskill_asset
10
+ - mcp__sellable__get_auth_status
11
+ - mcp__sellable__get_active_workspace
12
+ - mcp__sellable__list_workspaces
13
+ - mcp__sellable__get_workspace
14
+ ---
15
+
16
+ # Refill Sends Evergreen
17
+
18
+ Use this public command wrapper for evergreen waterfall refill requests such as
19
+ "refill evergreen", "fill evergreen senders", "load evergreen lanes", or
20
+ "plan evergreen refill".
21
+
22
+ Host command names:
23
+
24
+ - Claude Code: `/sellable:refill-sends-evergreen`
25
+ - Codex: `$sellable:refill-sends-evergreen`
26
+
27
+ Phase 85 is read-only, dry-run, zero mutations. It plans the deterministic
28
+ waterfall-ladder refill packet and writes a local dry-run journal, but it does
29
+ not prepare messages, approve messages, start campaigns, schedule sends, send
30
+ messages, refresh paid InMail credit facts, create campaigns, or change source
31
+ configuration. Execution ships in the follow-up phase.
32
+
33
+ ## Entry
34
+
35
+ Resolve the explicit `workspaceId` from the request, automation config, or
36
+ active workspace readback. Scheduled or autonomous usage must carry
37
+ `workspaceId` on every tool call. If the workspace is missing or ambiguous, stop
38
+ with `WORKSPACE_REQUIRED`; do not switch the shared active workspace.
39
+
40
+ Start with the command contract:
41
+
42
+ ```text
43
+ refill_sends_evergreen({ workspaceId })
44
+ ```
45
+
46
+ Then load the internal workflow prompt and flow asset:
47
+
48
+ ```text
49
+ get_subskill_prompt({ subskillName: "refill-sends-evergreen-workflow" })
50
+ get_subskill_asset({ subskillName: "refill-sends-evergreen-workflow", assetPath: "core/flow.v1.json" })
51
+ ```
52
+
53
+ Continue both loads until `hasMore:false`; parse the flow JSON and verify
54
+ `workflow:"refill-sends-evergreen-workflow"` with a `v1` version before the
55
+ planner call.
56
+
57
+ Call the dry-run planner with the explicit workspace id:
58
+
59
+ ```text
60
+ get_evergreen_refill_plan({ workspaceId, senderIds?, runState?, journal?, journalNote? })
61
+ ```
62
+
63
+ Use `senderIds` only when the user scoped the request to exact senders. Use
64
+ `runState` only for an explicit what-if dry run; otherwise let the MCP read
65
+ local lane memory hints. Leave `journal` enabled unless the user specifically
66
+ asked for no local journal.
67
+
68
+ ## Report
69
+
70
+ Review the returned packet before giving a recommendation:
71
+
72
+ - `planRevision` starts with `pr1:`.
73
+ - `stateRevision` identifies the current readback.
74
+ - `packet` is the operator-facing facts receipt.
75
+ - `plans[]` contains per-sender lane decisions and itinerary details.
76
+ - `globalActionQueue[]` is a dry-run sequence only in Phase 85.
77
+ - `evergreen.enumeratedRungs` and each action's `evergreenRung` map to the
78
+ locked ladder from the workflow asset.
79
+ - `journalPath` points to the dry-run markdown journal written by the MCP.
80
+ - `sideEffects` must be all false.
81
+
82
+ Report campaign names and sender names first, ids second. Include the chosen
83
+ rung, the itinerary, the plan revision, the journal path, and any blockers or
84
+ warnings. Stop after the report; do not execute the action queue in Phase 85.