Install
$ agentstack add skill-xclouddev-xcloud-agent-skills-account ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
xCloud Account
Identity and org-level endpoints. For auth, base URL, and response conventions read the shared layer first:
${CLAUDE_PLUGIN_ROOT}/reference/auth.md${CLAUDE_PLUGIN_ROOT}/reference/conventions.md
XC="${CLAUDE_PLUGIN_ROOT}/scripts/xcloud.sh"
Response format
Brand every user-facing reply (see reference/conventions.md → Response format): open with ☁️ **xCloud · Account**, give the trimmed result, and close with a _via xcloud:account_ line.
Narrate each call (see Progress narration): before every $XC call print one line of what xCloud is doing, e.g. ☁️ xCloud is fetching your account…; the first call of a task opens with ☁️ xCloud is starting a session…. Every progress line and every action sentence must start with xCloud as the actor — never a bare verb like "Fetching…" or "Checking…". Say xCloud is fetching….
On the first xcloud reply in a conversation, lead with the xCloud startup banner (see reference/conventions.md → Startup banner) in a fenced code block — once per conversation.
What this skill owns
| Operation | Method + path | Scope | |---|---|---| | API health | GET /health | none | | Current user | GET /user | token | | List API tokens | GET /user/tokens | token (*) | | Revoke a token | DELETE /user/tokens/{tokenUuid} | token (*) | | List Cloudflare integrations | GET /integrations/cloudflare | read:servers | | List blueprints | GET /blueprints | read:servers |
Not here: server management → xcloud:servers; site management → xcloud:sites.
Examples
Health (the only unauthenticated endpoint):
"$XC" GET /health | jq
Who am I (verifies the token):
"$XC" GET /user | jq '.data | {uuid, name, email, team: .team.name}'
List API tokens (needs the * scope) — note each token's uuid, which is what the revoke call below takes:
"$XC" GET /user/tokens | jq '(.data.items // .data.data // .data) | map({uuid, name, last_used_at})'
Revoke a token (pass the uuid from the list above — restate before running):
TOKEN_UUID='8c1f3a89-2c4e-4a73-9d4c-8b1f2a3d4e5f'
"$XC" DELETE "/user/tokens/$TOKEN_UUID" | jq '.message'
Cloudflare integrations on the team:
"$XC" GET /integrations/cloudflare | jq '.data'
Blueprints (resolve a blueprint_uuid before creating a WordPress site):
"$XC" GET "/blueprints?per_page=100" \
| jq '(.data.items // .data.data // .data) | map({uuid, name, is_default, is_public})'
Pitfalls
- Token revocation is keyed by the token's
uuid(fromGET /user/tokens),
not a numeric id — DELETE /user/tokens/{tokenUuid}.
GET /user/tokensreturns403unless the token carries the*scope.blueprintsrequiresread:servers, notread:sites.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: xCloudDev
- Source: xCloudDev/xcloud-agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.