Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sky-cloak/skycloak-mcp --skill keycloak-migration-doctorgit clone --depth 1 https://github.com/sky-cloak/skycloak-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sky-cloak/skycloak-mcp/keycloak-migration-doctor)<a href="https://agentmods.dev/skills/sky-cloak/skycloak-mcp/keycloak-migration-doctor"><img src="https://agentmods.dev/badge/skills/sky-cloak/skycloak-mcp/keycloak-migration-doctor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sky-cloak/skycloak-mcp/keycloak-migration-doctor"><img src="https://agentmods.dev/badge/skills/sky-cloak/skycloak-mcp/keycloak-migration-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.01507 |
| Opus 5 | $0.00036 | $0.00754 |
| Sonnet 5 | $0.00014 | $0.00301 |
| Haiku 4.5 | $0.00007 | $0.00151 |
Grade A, and why
keycloak-migration-doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keycloak migration doctor
Export and import failures look opaque because the dashboard notice is generic: "Job has reached the specified backoff limit" is a retry counter, not a cause. The cause is usually in the job record already, in the error_message field that skycloak_get_export, skycloak_get_realm_export and skycloak_get_realm_import all return. Reading it is the single highest-value step here. If a job has already failed, go straight to Diagnose; if the move has not run yet, start with Preflight.
Preflight: before an export, import or migration
- Pin down the unit with the user: a whole-cluster database dump
(skycloak_create_export), one realm's archive
(skycloak_create_realm_export), or a realm import into Skycloak
(skycloak_create_realm_import). Find the cluster with
skycloak_list_clusters, then skycloak_get_cluster: it must be
available, and note its Keycloak version, because an archive from a newer major does not import into an older target. - For an import, call skycloak_list_realms on the target: the import refuses a realm-name collision with a 409 rather than overwriting, so a taken name is better discovered now than on migration day.
- Check the known blockers, all taken from support history:
- Script-based authorization policies. Current Keycloak only loads JavaScript policies packaged in a deployed scripts JAR, so realms whose clients still carry admin-console script policies fail; the classic offender is a policy named "Default Policy" that old versions auto-created on authorization-enabled clients. No tool lists client policies, so use skycloak_list_applications to enumerate the clients and have the user clear script policies under each client's Authorization > Policies in the admin console. The dry run below catches any they miss.
- The legacy
/authpath. Keycloak dropped the/authURL prefix in 17 and Skycloak clusters serve the modern paths, so anything with the old prefix hard-coded breaks after the move even though the import itself succeeds. Ask now. - partial-export never includes users. Keycloak's built-in partial export excludes users by design. A plan of "partial export, import, log in" fails at the login, not the import; users need a full realm export.
- Feature flags. If the source relies on a Keycloak feature flag, check skycloak_list_cluster_features. A flag absent from that list is reserved for the platform operator; escalate rather than promise it.
- Dry run now. The cheapest preflight is running the export today and polling it: a failure with error_message in hand this week beats the same failure on migration day. Realm archives are always encrypted: ask the user for a password, never invent one, and say the same password is needed again at import.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 117 lines · 72 tokens per session scan A ff062180dc2f
keycloak-migration-doctor is a skill published in the GitHub repository sky-cloak/skycloak-mcp (0 stars, last pushed 5d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,507 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
zeroid
MANUAL TRIGGER ONLY: invoke only when user types /zeroid. Identity infrastructure for AI agents — register identities, issue tokens, delegate to sub-agents, revoke credentials, and manage credential policies via the Zeroid REST API.
functions-development
Build serverless Go or Python functions for Falcon Foundry apps. TRIGGER when user asks to "create a function", "write a serverless function", "build backend logic", runs foundry functions create, or needs help with FDK handler patterns, function testing, or collection integration from functions. Also TRIGGER when…
explain-error
Explain an error message with optional context.
configuring-oauth2-authorization-flow
Configure secure OAuth 2.0 authorization flows including Authorization Code with PKCE, Client Credentials, and Device Authorization Grant. This skill covers flow selection, PKCE implementation, token.
configuring-ldap-security-hardening
Harden LDAP directory services against common attacks including credential harvesting, LDAP injection, anonymous binding, and channel binding bypass. Covers LDAPS enforcement, channel binding, LDAP si.