@sellable/mcp 0.1.375 → 0.1.377
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
CHANGED
|
@@ -16,10 +16,11 @@ Each message gets 5+ minutes of Claude attention with deep research - no other t
|
|
|
16
16
|
|
|
17
17
|
### Prompt Source Of Truth
|
|
18
18
|
|
|
19
|
-
There are
|
|
19
|
+
There are six public Sellable entrypoints shared across hosts:
|
|
20
20
|
|
|
21
21
|
- `sellable:create-campaign`
|
|
22
22
|
- `sellable:create-ab-test`
|
|
23
|
+
- `sellable:create-evergreen-campaigns`
|
|
23
24
|
- `sellable:foundation`
|
|
24
25
|
- `sellable:content`
|
|
25
26
|
- `sellable:create-post`
|
|
@@ -35,6 +36,11 @@ review-copy campaigns from:
|
|
|
35
36
|
|
|
36
37
|
- `mcp/sellable/skills/create-ab-test/SKILL.md`
|
|
37
38
|
|
|
39
|
+
The create-evergreen-campaigns public wrapper reconciles standing evergreen
|
|
40
|
+
campaign lanes and loads the command-backed setup workflow from:
|
|
41
|
+
|
|
42
|
+
- `mcp/sellable/skills/create-evergreen-campaigns/SKILL.md`
|
|
43
|
+
|
|
38
44
|
The foundation public wrapper loads the core identity/company memory workflow
|
|
39
45
|
from:
|
|
40
46
|
|
|
@@ -179,9 +185,11 @@ The installer does the full local setup:
|
|
|
179
185
|
|
|
180
186
|
After the installer passes, fully quit and reopen Codex Desktop. Start a new
|
|
181
187
|
thread and select `Sellable Create Campaign`, `Sellable Create A/B Test`,
|
|
182
|
-
`Sellable
|
|
188
|
+
`Sellable Create Evergreen Campaigns`, `Sellable Foundation`,
|
|
189
|
+
`Sellable Content`, or `Sellable Create Post`; or invoke
|
|
183
190
|
`$sellable:create-campaign`, `$sellable:create-ab-test`,
|
|
184
|
-
`$sellable:
|
|
191
|
+
`$sellable:create-evergreen-campaigns`, `$sellable:foundation`,
|
|
192
|
+
`$sellable:content`, or `$sellable:create-post`. If the app still says
|
|
185
193
|
`mcp__sellable__*` tools are missing after the installer passes, check that
|
|
186
194
|
`~/.codex/config.toml` contains both `[marketplaces.sellable]` and
|
|
187
195
|
`[plugins."sellable@sellable"]`.
|
|
@@ -194,22 +202,26 @@ Use these names consistently:
|
|
|
194
202
|
|
|
195
203
|
- Claude Code command: `/sellable:create-campaign`
|
|
196
204
|
- Claude Code command: `/sellable:create-ab-test`
|
|
205
|
+
- Claude Code command: `/sellable:create-evergreen-campaigns`
|
|
197
206
|
- Claude Code command: `/sellable:foundation`
|
|
198
207
|
- Claude Code command: `/sellable:content`
|
|
199
208
|
- Claude Code command: `/sellable:create-post`
|
|
200
209
|
- Codex command: `$sellable:create-campaign`
|
|
201
210
|
- Codex command: `$sellable:create-ab-test`
|
|
211
|
+
- Codex command: `$sellable:create-evergreen-campaigns`
|
|
202
212
|
- Codex command: `$sellable:foundation`
|
|
203
213
|
- Codex command: `$sellable:content`
|
|
204
214
|
- Codex command: `$sellable:create-post`
|
|
205
215
|
- Codex Desktop plugin: `sellable@sellable`
|
|
206
216
|
- Codex visible skill: `Sellable Create Campaign`
|
|
207
217
|
- Codex visible skill: `Sellable Create A/B Test`
|
|
218
|
+
- Codex visible skill: `Sellable Create Evergreen Campaigns`
|
|
208
219
|
- Codex visible skill: `Sellable Foundation`
|
|
209
220
|
- Codex visible skill: `Sellable Content`
|
|
210
221
|
- Codex visible skill: `Sellable Create Post`
|
|
211
222
|
- Codex skill frontmatter name: `create-campaign`
|
|
212
223
|
- Codex skill frontmatter name: `create-ab-test`
|
|
224
|
+
- Codex skill frontmatter name: `create-evergreen-campaigns`
|
|
213
225
|
- Codex skill frontmatter name: `foundation`
|
|
214
226
|
- Codex skill frontmatter name: `content`
|
|
215
227
|
- Codex skill frontmatter name: `create-post`
|
|
@@ -6,7 +6,7 @@ async function postSetupEvergreenCampaigns(body) {
|
|
|
6
6
|
export const setupEvergreenCampaignsToolDefinitions = [
|
|
7
7
|
{
|
|
8
8
|
name: "setup_evergreen_campaigns",
|
|
9
|
-
description: "Evergreen campaign setup plan/verify command. Use plan mode first to inspect exact workspace/sender/campaign/table/source state and receive immutable lane packets. `selectedSenderIds` is a legacy shorthand for both scopes; prefer `postEngagerSenderIds` for the Post Engagers sender scope and `sharedSenderIds` for the shared lane sender scope when they differ. The command plans one Post Engagers lane per post-engager sender plus shared Signal Discovery and Shared Cold Fallback lanes for the shared sender set. yolo is only a parent-skill auto-execution hint for safe lane packets; this backend command remains read-only in plan mode and verifies receipts in verify mode. Package-backed prompt authority: lane workers must use get_subskill_prompt and get_subskill_asset for `$sellable:create-campaign`, create-campaign-v2, generate-messages, and assets; filesystem prompt fallback is a failed UAT. Use mcp__sellable only for workspace selection and product mutations/readbacks. Do not use mcp__sellable_admin, direct DB, Prisma, or SQL as execution proof. Worker-local replans are read-only drift checks and must preserve the exact parent sender scopes, including postEngagerSenderIds:[] when intentionally empty and the exact sharedSenderIds array; if scope, planRevision, actionId, or laneKey drifts, stop with blocked:worker_plan_scope_drift before mutation. Each lane packet includes workerDispatch with acceptedRuntimes, rejectedRuntimes, requiresVisibleThreadOrDurableReceipt, and
|
|
9
|
+
description: "Evergreen campaign setup plan/verify command. Use plan mode first to inspect exact workspace/sender/campaign/table/source state and receive immutable lane packets. `selectedSenderIds` is a legacy shorthand for both scopes; prefer `postEngagerSenderIds` for the Post Engagers sender scope and `sharedSenderIds` for the shared lane sender scope when they differ. The command plans one Post Engagers lane per post-engager sender plus shared Signal Discovery and Shared Cold Fallback lanes for the shared sender set. yolo is only a parent-skill auto-execution hint for safe lane packets; this backend command remains read-only in plan mode and verifies receipts in verify mode. Package-backed prompt authority: the installed public wrapper can be the local Codex skill entrypoint, but lane workers must use get_subskill_prompt and get_subskill_asset for nested `$sellable:create-campaign`, create-campaign-v2, generate-messages, validation, and assets; nested filesystem prompt fallback is a failed UAT. Use mcp__sellable only for workspace selection and product mutations/readbacks. Do not use mcp__sellable_admin, direct DB, Prisma, or SQL as execution proof. Worker-local replans are read-only drift checks and must preserve the exact parent sender scopes, including postEngagerSenderIds:[] when intentionally empty and the exact sharedSenderIds array; if scope, planRevision, actionId, or laneKey drifts, stop with blocked:worker_plan_scope_drift before mutation. Each lane packet includes workerDispatch with acceptedRuntimes, rejectedRuntimes, requiresVisibleThreadOrDurableReceipt, receiptArtifactHint, receiptRunId, and receiptMustBeWrittenAfter; pre-existing receipts at old deterministic paths are stale and must not be used, so stop with blocked:stale_receipt_artifact if the receipt was not freshly written for the current receiptRunId. `multi_agent_v1.spawn_agent`/opaque spawn_agent is not accepted for mutating command proof unless the parent has visible thread or durable receipt proof. In local Codex, call `codex_app.list_projects` first, then `codex_app.create_thread` with a local project target; do not create a worktree for lane execution. When safe-yolo needs normal setup work, the parent skill may ask for bounded delegated approval: one approval over the current planRevision, selected action ids, caps, allowed side-effect classes, and stop conditions lets lane workers execute without per-substep approval while staying inside that packet. Lane workers must explicitly load and use the installed `$sellable:create-campaign` wrapper as the nested workflow entrypoint, then load `create-campaign-v2` and `create-campaign-v2/core/flow.v2.json`; they must execute creation, source import, create-campaign workflow steps, generate-messages, sequence attachment, pause_campaign review-state transition when the current table is still DRAFT, and review readiness through that existing create-campaign workflow/subskills, then return receipts here for verification. Customer-visible verify receipts must set status:'succeeded' or status:'completed'; status:'passed', status:'pass', and status:'passed_with_warnings' are rejected as primary success statuses. Receipts must include createCampaignStepReceipt with setupPlanCall, createCampaignWorkflowReceipt, campaignBriefReceipt, sourceDecisionReceipt, filterDecisionReceipt, messageDraftingReceipt, reviewBatchReceipt, sequenceReceipt, and verifyCall nested inside createCampaignStepReceipt; top-level-only copies of those objects are not enough and are not promoted by verify. setupPlanCall must use canonical keys: planRevision, actionId, laneKey, workspaceId, senderIds, campaignId, tableId, createIntent. Do not use laneActionId, lanePacketActionId, delegatedPlanRevision, delegatedActionId, or requestedCall text as a substitute for those canonical fields. createCampaignWorkflowReceipt must include skillCommand:'$sellable:create-campaign', skillName:'create-campaign', wrapperSkillLoaded:true, workflowPromptName:'create-campaign-v2', workflowPromptLoadedToHasMoreFalse:true, workflowAssetPath:'create-campaign-v2/core/flow.v2.json', workflowAssetLoaded:true, workerRuntime, workerThreadId or receiptArtifactPath, durableReceiptWritten when using a receipt file, and notAdHoc:true. messageDraftingReceipt must use exactly statusSource:'branch' or statusSource:'packaged-generate-messages-worker'; descriptive aliases such as statusSource:'package-readback-local-thread' are rejected. It must include proof that generate-messages was loaded, start_campaign_message_preparation/get_campaign_message_preparation_status ran when the packaged worker path is used, validationResult:'passed', a passed qualityReview, and at least 3 concrete sampleMessages with rowId, generatedMessageText, verdict, and issues; Do not substitute `message` for `generatedMessageText`; Do not substitute `passVerdict` for `verdict`. Before writing durable receipts, run a receipt self-check: top-level `planRevision`, `actionId`, `laneKey`, `laneType`, `workspaceId`, and `senderIds` must exist; if the self-check fails, fix the receipt before ending. Use start_campaign_message_preparation with approvalMode:\"mark_ready\" only for evergreen setup. Never call `start_campaign_message_preparation` with `approvalMode:\"approve\"`; approve exactly one semantic Approved cell through select_campaign_cells/update_cell and final proof must show approvedGeneratedMessageCount exactly 1. Shared Cold Fallback samples with a standalone name followed by 'Hey there' are rejected. This command does not launch campaigns, does not schedule sends, does not assign scheduler-owned send fields, does not raw-write campaign status, does not archive/delete cleanup targets, and does not spend paid credits.",
|
|
10
10
|
inputSchema: {
|
|
11
11
|
type: "object",
|
|
12
12
|
properties: {
|
package/package.json
CHANGED
|
@@ -73,18 +73,26 @@ readback, and setup plan/verify results. If MCP surfaces disagree on counts or
|
|
|
73
73
|
state, record the discrepancy and resolve or explain the canonical gate before
|
|
74
74
|
reporting the command complete.
|
|
75
75
|
|
|
76
|
-
Package-backed prompt authority:
|
|
77
|
-
load
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
76
|
+
Package-backed prompt authority: this public wrapper is an installed Codex
|
|
77
|
+
skill, so the host may load the wrapper itself from the local plugin bundle as
|
|
78
|
+
the command entrypoint. That entrypoint load is allowed, but it is not proof
|
|
79
|
+
that the create-campaign workflow ran. After this wrapper is active, when this
|
|
80
|
+
command or any lane worker says to load `$sellable:create-campaign`,
|
|
81
|
+
`create-campaign-v2`, `generate-messages`, validation, or any referenced
|
|
82
|
+
workflow asset, the package-backed MCP loaders are the source of truth. Use
|
|
83
|
+
`get_subskill_prompt` and `get_subskill_asset` until `hasMore:false`.
|
|
84
|
+
Do not locate, open, read, or summarize nested workflow prompt files from repo
|
|
85
|
+
paths, installed plugin cache paths, or any filesystem shortcut. Do not use
|
|
86
|
+
repo-local, plugin-cache, or filesystem `SKILL.md` files as nested workflow
|
|
87
|
+
authority, even when a session header shows a path. If package-backed prompt or
|
|
88
|
+
asset loaders are not callable, stop with
|
|
89
|
+
`blocked: package_prompt_loader_unavailable`; nested filesystem prompt fallback
|
|
90
|
+
is a failed UAT and is not proof that the packaged workflow ran.
|
|
91
|
+
Short form: The installed wrapper can be the entrypoint; nested workflow prompts
|
|
92
|
+
must use MCP loaders.
|
|
93
|
+
Short form: Do not use repo-local, plugin-cache, or filesystem nested
|
|
94
|
+
`SKILL.md` files as workflow authority.
|
|
95
|
+
Short form: nested filesystem prompt fallback is a failed UAT.
|
|
88
96
|
|
|
89
97
|
Package-backed tool surface: use `mcp__sellable` only for workspace selection,
|
|
90
98
|
campaign/table/source/message mutations, and product-visible readbacks. Do not
|
|
@@ -199,8 +207,18 @@ environment:{type:"local"}}`. Do not create a worktree target for evergreen
|
|
|
199
207
|
UAT or lane execution. The parent must record the returned thread id, pass
|
|
200
208
|
exactly one lane packet into that thread, and require the worker to write the
|
|
201
209
|
lane receipt at the artifact path named by
|
|
202
|
-
`workerDispatch.receiptArtifactHint`.
|
|
203
|
-
|
|
210
|
+
`workerDispatch.receiptArtifactHint`. That path is run-specific and must include
|
|
211
|
+
the packet's `workerDispatch.receiptRunId`. Before dispatch, if a file already
|
|
212
|
+
exists at the hinted path, do not trust or verify it; move it aside or choose the
|
|
213
|
+
fresh hinted path from a new plan. A valid receipt must be written after
|
|
214
|
+
`workerDispatch.receiptMustBeWrittenAfter`, reread by the parent after the
|
|
215
|
+
worker exits, and contain the current `planRevision`, `actionId`, `laneKey`,
|
|
216
|
+
`receiptArtifactPath`, and `durableReceiptWritten:true`. If a receipt predates
|
|
217
|
+
the current run, uses an old path without `receiptRunId`, or was not freshly
|
|
218
|
+
written by the current worker, stop with `blocked: stale_receipt_artifact`
|
|
219
|
+
before parent verify or completion. A streaming worker or branch worker is
|
|
220
|
+
acceptable only when it writes a fresh durable per-lane receipt artifact as it
|
|
221
|
+
works.
|
|
204
222
|
`multi_agent_v1.spawn_agent`, raw `spawn_agent`, or any opaque Task/subagent
|
|
205
223
|
runtime that cannot expose a visible thread id or durable receipt artifact is
|
|
206
224
|
not accepted as command-level UAT proof and must not be used for mutating
|
|
@@ -366,7 +384,7 @@ verification unless the same object also appears inside
|
|
|
366
384
|
"workflowAssetLoaded": true,
|
|
367
385
|
"workerRuntime": "separate-codex-thread",
|
|
368
386
|
"workerThreadId": "<visible local Codex thread id>",
|
|
369
|
-
"receiptArtifactPath": ".planning/artifacts/uat/69/lane-receipts/<planRevision>/<actionId>-<laneKey>.json",
|
|
387
|
+
"receiptArtifactPath": ".planning/artifacts/uat/69/lane-receipts/<planRevision>/<receiptRunId>/<actionId>-<laneKey>.json",
|
|
370
388
|
"durableReceiptWritten": true,
|
|
371
389
|
"notAdHoc": true
|
|
372
390
|
},
|