@ssheleg/sheleg-dev 0.13.1 → 0.13.2

package/CHANGELOG.md

@@ -1,3 +1,10 @@
+## v0.13.2 — setup follows host capabilities
+
+Error tracking no longer assumes every non-Claude host lacks MCP or that setup
+works only in Claude Code and Cursor. It checks the active host prerequisites,
+keeps CLI/SDK fallback, and labels the Claude MCP command as host-specific.
+A skills-only installation does not claim to register MCP or hooks.
+
 ## v0.13.1 — a payment bug reaches the billing skill
 
 The 2026-10-08 family routing audit found that a request opening with the symptom rather

package/README.md

@@ -12,6 +12,10 @@
 npx skills add ssheleg/sheleg-dev
 ```
 
+For error-tracking setup, check the host's shell, network, install permissions
+and available integrations. The skill's CLI/SDK route is not restricted to
+Claude Code or Cursor; a skills-only install does not register MCP or hooks.
+
 Ask: `Wire Stripe subscriptions so access follows verified webhook state exactly once.`
 
 **[Detailed docs →](https://skills.sshlg.me/skills/sheleg-dev/)**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ssheleg/sheleg-dev",
-  "version": "0.13.1",
+  "version": "0.13.2",
   "description": "Seven integration skills for the layer a product reaches once it has users: Stripe subscription billing and cancellation retention, crypto payments, ad and conversion tracking under Consent Mode v2, Google sign-in and the wider Google auth surface, error tracking, and Core Web Vitals. This package is the installer CLI.",
   "bin": {
     "sheleg-dev": "bin/sheleg-dev.js"

package/plugins/sheleg-dev/.claude-plugin/plugin.json

@@ -3,7 +3,7 @@
   "name": "sheleg-dev",
   "displayName": "Sheleg Dev",
   "description": "The integration layer a product needs once it has users: Stripe subscription billing reconciled into your own database, crypto payments that survive over-payment and duplicate webhooks, ad and conversion tracking under Consent Mode v2, Google sign-in with the account-linking guards, the wider Google auth surface, and Core Web Vitals work that moves the score, and Sentry error tracking wired so it does not forward your own credentials to a third party and so a stack trace names the commit that caused it.",
-  "version": "0.13.1",
+  "version": "0.13.2",
   "author": {
     "name": "ssheleg",
     "url": "https://x.com/sshlg93"

package/plugins/sheleg-dev/skills/error-tracking/SKILL.md

@@ -257,10 +257,12 @@ cover the shape where a job stops running.
 
 ## Degradation
 
-- **Not Claude Code** (Cursor, Codex, skills CLI, the API container): no MCP, no
-  `/command`. Everything here is CLI and SDK, both of which work anywhere with a
-  shell — except the API container, which has no network and no package install,
-  so treat this skill as Claude Code and Cursor only for the setup half.
+- **Host capabilities vary:** check the current client's shell, network,
+  package-install permissions, MCP and skill invocation support. Do not infer
+  their absence from a non-Claude host name. Use the CLI/SDK route when its
+  prerequisites exist; in a restricted container, name the unavailable step
+  and prepare the configuration without claiming setup ran. A skills-only
+  install does not register plugin commands, MCP servers or hooks.
 - **`sentry` CLI absent**: say so once, then use the REST API directly with a
   token (`curl https://sentry.io/api/0/…`), or the web UI for the one-off. Do
   not loop on the missing binary.

package/plugins/sheleg-dev/skills/error-tracking/references/setup.md

@@ -137,6 +137,10 @@ gateway must reject the mismatch and the flow cannot complete.
 claude mcp add --transport http sentry https://mcp.sentry.dev/mcp/<org>/<project>
 ```
 
+That command is for Claude Code. Other clients use their own supported MCP
+configuration and OAuth flow; inspect the current host's instructions instead
+of executing a Claude command there. If MCP is unavailable, use the CLI route.
+
 Scoping is optional and narrows what the server sees:
 `…/mcp`, `…/mcp/<org>`, `…/mcp/<org>/<project>`. Narrow it.