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 monkilabs/opencastle --skill cloudflare-platformgit clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/monkilabs/opencastle/cloudflare-platform)<a href="https://agentmods.dev/skills/monkilabs/opencastle/cloudflare-platform"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/cloudflare-platform/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/monkilabs/opencastle/cloudflare-platform"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/cloudflare-platform.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 | $0.00054 | $0.00536 |
| Opus 5.5 | $0.00022 | $0.00214 |
| Sonnet 5.5 | $0.00011 | $0.00107 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
cloudflare-platform 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 11d 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.
What it actually says
Cloudflare Platform
Workers
- V8 isolates, not Node:
process,Buffer,fsdo not exist unlesscompatibility_flags = ["nodejs_compat"]is set.compatibility_datemust be set or deploys fail. - Worker size limit is 3 MB compressed on the Free plan, 10 MB on Paid. Keep dependencies minimal.
ctx.waitUntil(promise)for side effects that must outlive the response (logging, analytics).- Bindings are reachable only via the handler's
envargument, and must exist in bothwrangler.tomland theEnvinterface. - Durable Objects need
[[durable_objects.bindings]]and a[[migrations]]block withnew_classes = ["Counter"]— the binding alone will not deploy.
Storage selection
KV: config/sessions/cache, eventually consistent. D1: relational SQLite, strongly consistent. R2: files/blobs, S3-compatible, no egress cost. Durable Objects: coordination, counters, locks, realtime. Queues: async jobs.
Limits: KV value 25MB, key 512 bytes, metadata 1024 bytes, read lag up to 60s. R2 needs multipart upload above 100MB. D1 is SQLite — no MySQL/Postgres-only syntax; always .bind() params; env.DB.batch([...]) collapses round trips.
Wrangler
wrangler secret put NAME [--env staging]— secrets never live inwrangler.toml; local dev uses.dev.vars.- KV bindings need
preview_idforwrangler dev --remote. - D1 migrations: pass the target explicitly —
wrangler d1 migrations apply <db> --localfor dev,--remotefor production. wrangler tailfor live production logs;wrangler deployments list+wrangler rollback <version-id>;wrangler whoamito confirm the account.
MCP
Code Mode exposes exactly two tools: search (Cloudflare API spec) and execute (JavaScript against the API). ~1k tokens per operation vs ~244k for native tool exposure.
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.
- 11d ago Changed · -21 tokens per session 212f81a650c4
- 12d ago First seen · 34 lines · 75 tokens per session scan A 9b000f03ec48
cloudflare-platform is a skill published in the GitHub repository monkilabs/opencastle (80 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 536 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
telnyx-storage-curl
Manage cloud storage buckets and objects using the S3-compatible Telnyx Storage API. This skill provides REST API (curl) examples.
orchardcore-ai-documents-azure-storage
Skill for storing CrestApps Orchard Core AI Documents in Azure Blob Storage. Covers AIDocumentBlobStorageOptions, BlobFileStore replacement, tenant container lifecycle, cleanup choices, and Azure configuration. Use this skill when requests mention Orchard Core AI Documents Azure Blob Storage…
orchardcore-omnichannel-event-grid
Skill for receiving and dispatching Omnichannel events through Azure Event Grid in Orchard Core using CrestApps modules. Covers webhook authentication, Event Grid subscription validation, inbound message persistence, event handler dispatch, and tenant configuration. Use this skill when requests mention Orchard Core…
orchardcore-configuration
Skill for configuring Orchard Core applications. Covers IShellConfiguration, configuration sources hierarchy, tenant pre-configuration and post-configuration, environment variable overrides, appsettings.json structure, IOptions patterns, and deployment configuration. Use this skill when requests mention Orchard Core…
orchardcore-health-checks
Skill for exposing and extending Orchard Core tenant health checks. Covers HealthChecksOptions, health endpoint configuration, IHealthCheck registration, detailed JSON responses, IHealthChecksResponseWriter customization, and ASP.NET Core health check integration. Use this skill when requests mention Orchard Core…
alibaba-event-driven-architecture-review
Review Alibaba Cloud EventBridge, MNS (Message Notification Service), RocketMQ, and MSE event-driven designs — dead-letter queues, message ordering, idempotency, retry storm prevention, schema registry, and consumer group lag monitoring.