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-upgrade-readinessgit 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-upgrade-readiness)<a href="https://agentmods.dev/skills/sky-cloak/skycloak-mcp/keycloak-upgrade-readiness"><img src="https://agentmods.dev/badge/skills/sky-cloak/skycloak-mcp/keycloak-upgrade-readiness/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-upgrade-readiness"><img src="https://agentmods.dev/badge/skills/sky-cloak/skycloak-mcp/keycloak-upgrade-readiness.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 | $0.00058 | $0.01095 |
| Opus 5 | $0.00029 | $0.00548 |
| Sonnet 5 | $0.00012 | $0.00219 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
keycloak-upgrade-readiness 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keycloak upgrade readiness
Upgrading Keycloak is a database migration wearing a version number. The migrations run at startup and are one-way: once a cluster has started on the new version, the only road back is restoring an export taken before the upgrade. Plan accordingly, and never treat this as "bump the version field".
Phase 1: assess the estate
- Call skycloak_list_clusters and record, per cluster: type, current version,
status, and whether auto_upgrade_enabled is set. A cluster that is not
availableis not a candidate for anything until it is. - For each cluster type in use, call skycloak_list_cluster_versions to learn the newest version offered. Rank clusters by how far behind they are.
- For each cluster that is behind, call skycloak_get_cluster_upgrade_path. The path is the authority on sequencing: follow its steps in order and do not invent shortcuts across majors, even when the API would accept the target version directly. Keycloak ships roughly three majors a year and only the newest line receives fixes, so "furthest behind" is also "most exposed".
- Call skycloak_list_cluster_upgrades for recent history. A previously failed or cancelled upgrade on the same cluster is a red flag to explain before retrying, not to retry past.
Phase 2: what the new version breaks
Work through these for every step in the path, using the release notes for that version as the checklist. The usual suspects, most breakage first:
- Extensions. Keycloak's server SPIs are not stable across majors: a provider compiled against one major can fail to deploy on the next. Call skycloak_list_cluster_extensions for each cluster, then skycloak_list_extensions to see whether newer builds of those extensions exist. Upgrade the extension first with skycloak_upgrade_extension where a compatible build is available; where none is, the cluster upgrade waits.
- Custom themes. FreeMarker templates and the login form structure change between majors. Call skycloak_list_themes and note which realms carry a custom theme; those realms need a visual check of the login, registration and email templates after each upgrade step.
- Deprecated surfaces. Very old estates may still have clients using
removed adapter endpoints or the legacy
/authpath prefix. Flag them now; they fail loudly after the upgrade, not before.
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 · 90 lines · 58 tokens per session scan A 157c617bdab6
keycloak-upgrade-readiness is a skill published in the GitHub repository sky-cloak/skycloak-mcp (0 stars, last pushed 5d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,095 once invoked, about $0.0003 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
code-review
Structured code review prompt with language and focus area.
pr-to-go-linter
Generate a new pkg/linters analyzer from a merged or open PR pattern.
go-concurrency-safety
L1 supplement - audits Go-specific concurrency hazards in node client code: map iteration non-determinism, goroutine leaks, mutex ordering, panic boundaries, context cancellation.
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
trace-mcp-refactoring
Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.
ci-orchestrator
Run a CI-like pipeline locally (format, lint, vet, static-analysis, tests) and summarize per-step results with remediation guidance.