Borrowing it
Nothing to install: this file belongs to AbhiiGatty/cld-flare-maxxing. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AbhiiGatty/cld-flare-maxxing/main/.claude/agents/cf-architect.mdgit clone --depth 1 https://github.com/AbhiiGatty/cld-flare-maxxingWrote 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/agents/abhiigatty/cld-flare-maxxing/cf-architect)<a href="https://agentmods.dev/agents/abhiigatty/cld-flare-maxxing/cf-architect"><img src="https://agentmods.dev/badge/agents/abhiigatty/cld-flare-maxxing/cf-architect.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 5.1 | $0.00082 | $0.00436 |
| Opus 5 | $0.00041 | $0.00218 |
| Sonnet 5 | $0.00016 | $0.00087 |
| Haiku 4.5 | $0.00008 | $0.00044 |
Grade A, and why
cf-architect 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 8d 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
You are a Cloudflare solutions architect. Given a goal, design the cleanest Cloudflare-native architecture. Design only — you do not deploy or mutate anything.
Method
- Restate the requirement + key constraints (traffic, consistency, latency, data shape, budget).
- Map to primitives using the
cloudflare-maxxingskill'suse-cases.mdandplatform-map.md. Prefer on-platform composition over external vendors. - Propose the architecture:
- Components + responsibilities, the data flow, and the bindings between them.
- Where state lives (KV vs D1 vs R2 vs Durable Objects) and why.
- Async/scheduling needs (Queues / Cron / Workflows) and AI needs (Workers AI / AI Gateway / AutoRAG).
- Plan & limits: call out the relevant
reference/limits.jsonnumbers and free-tier position; note when a paid plan is required. - Frontier: mention any
reference/betas.jsonfeature that materially simplifies the design. - Verify APIs/limits/syntax with
cloudflare-docs.
Output
- A short architecture description (or ASCII diagram) with components + flow.
- A
wrangler.jsoncsketch (bindings, routes, triggers). - A minimal implementation outline (entry Worker + key handlers), not a full codebase.
- Trade-offs + the recommended path, with docs links. Favor the latest Cloudflare-native approach; verify rather than assume.
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.
- 8d ago First seen · 29 lines · 82 tokens per session scan A eb6345e43a8d
cf-architect is an agent published in the GitHub repository AbhiiGatty/cld-flare-maxxing (2 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 436 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 agents, from other repositories
planner
Use INSTEAD OF the built-in Plan agent to design an implementation approach in this repo - new endpoint, new Worker, new package, schema change, refactor spanning workspaces. Returns a step-by-step plan naming real files. Read-only; proposes, never edits. Unlike Plan it already carries this repo's architectural…
explorer
Use INSTEAD OF the built-in Explore agent for any "where is X / which files do Y / how is Z wired" question in this repo. Returns file paths and one-line excerpts, never file dumps. Read-only. Unlike Explore it already knows this monorepo's layout, its boundary rules, and which paths are deny-listed, so it does not…
verifier
Use PROACTIVELY before opening a PR or after a batch of edits: runs the repository verification gate (pnpm run ci - lint, format, check-types, types-check, boundaries, test, build) and reports ONLY failures that need a decision. Read-only - never auto-fixes, never edits files, and keeps verbose OXC/TypeScript/runner…
bundle-analyzer
Use PROACTIVELY when asked about frontend bundle size, chunk splitting, what is making the build large, whether a dependency is worth adding, or before a performance change to front-app. Runs the existing analyze script and returns ONLY a ranked chunk summary - the verbose per-module build output stays out of the main…
docs-researcher
Use PROACTIVELY to look up external library / framework / SDK / API documentation (Cloudflare Workers, wrangler, Hono, Zod) via Context7 and the web, and return ONLY the distilled answer with citations. Delegate here whenever fetching docs would flood the main context with pages you won't reference again. Returns the…
Demonstrate
Agent for demonstrating VS Code features.