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 agentmods add skills/humanerd-drew/opencode-drewgent/cloudflare-workers-deploynpx skills add humanerd-drew/opencode-drewgent --skill cloudflare-workers-deploygit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/cloudflare-workers-deploy)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/cloudflare-workers-deploy"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/cloudflare-workers-deploy.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.05779 |
| Opus 5 | $0.00016 | $0.02890 |
| Sonnet 5 | $0.00006 | $0.01156 |
| Haiku 4.5 | $0.00003 | $0.00578 |
Grade C, and why
cloudflare-workers-deploy scanned grade C with 2 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .wrangler/state/v3/d1/ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
let assetRes = await assets.fetch(request); How it starts
The opening of the file, as written. The whole thing — 568 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare Workers Deployment & Operations
Overview
Cloudflare Workers behave differently in local dev vs production deployment. This skill covers the operational gaps: secrets sync, network differences, timeout limits, and diagnostic procedures.
When to Use
- Deployed Worker fails but
wrangler devworks - Secrets / env vars don't appear in production
- Outbound API calls (NVIDIA, OpenAI, etc.) fail from Worker but work locally
wrangler deploysucceeds but endpoint returns errors
Core Principles
Local ≠ Deployed
wrangler dev runs on YOUR machine. These things are different in production:
| Aspect | wrangler dev (local) | wrangler deploy (Cloudflare) |
|---|---|---|
| Source IP | Your home/office IP | Cloudflare shared egress IP |
| Secrets source | .dev.vars file |
wrangler secret put values |
| Request timeout | Unlimited | 30s (free) / 30s per fetch (paid) |
| CPU time | Unlimited | 10s (free) / 30s (paid) / 30min (unbound) |
| Memory | Local | 128MB |
| DNS resolution | System resolver | Cloudflare resolver |
| Subrequests | Unlimited | 1000 per request |
Secrets are NOT Auto-Synced
.dev.vars — local development only, read by wrangler dev
wrangler secret put KEY — production secrets, separate store
Changing .dev.vars does NOT update production secrets. You must run wrangler secret put for each key.
Secrets Propagation
After wrangler secret put, secrets may take a few moments to propagate. If a test immediately after secret put fails, wait 30-60s or redeploy (wrangler deploy) to force a fresh version with the new secrets.
Diagnostic tip: If wrangler secret put reports success but the deployed worker still fails, and you changed the worker code at the same time, the deploy may have happened BEFORE the secret fully propagated. Run wrangler deploy again with no code changes — this creates a new version that picks up the current secret state.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 568 lines · 32 tokens per session scan C d7af1d438fd7
cloudflare-workers-deploy is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 5,779 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
alchemy-infra
Sets up Alchemy (alchemy-run/alchemy, Infrastructure-as-TypeScript) in any codebase — new project scaffold OR add to existing app. Wires Cloudflare/AWS providers, state backend, secrets, and binding types end-to-end with strict secret hygiene. USE THIS SKILL whenever the user mentions "alchemy", "alchemy.run"…
cloudflare-workers-debugging
Use when wrangler deploys silently fail or produce wrong artifacts, secrets upload as empty strings, custom domain DNS is not resolving, route assignment broke after rename, observability/tail logs are needed, D1/KV/R2 bindings are missing, OAuth scope errors block a command, cookies on a redirect are not attaching…
wrangler
Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over…
cloudflare-one-migrations
Plans migrations from Zscaler ZIA/ZPA, Palo Alto, legacy VPN, SWG, or SASE stacks to Cloudflare One. Use for migration assessments, policy mapping, rollout plans, and parity/gap analysis.
agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues…
cloudflare
Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval…