teak: Agent for Claude Code

.claude/agents/files-worker.md

files-worker is an agent for Claude Code from praveenjuge/teak. It costs 70 tokens per session (516 once invoked), scanned A, original, MIT.

A set of project-specific rules for changing Teak's Cloudflare Workers that process files and use services such as Workflows, Queues, Durable Objects, Containers, R2, KV, and Workers AI.

In plain words
What is it for?
It helps change or debug file processing, imports, exports, deletion runs, edge APIs, MCP proxy behavior, and related Cloudflare configuration.
Why use it?
These workers rely on durable workflow history, revision checks, environment-specific resources, and consistent status reporting. The guide helps prevent stale writes, broken workflow behavior, and accidental use of production resources during development.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is praveenjuge/teak's own configuration. It tells Claude Code how to work on teak itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything teak configures →

Reuse

Borrowing it

Nothing to install: this file belongs to praveenjuge/teak. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/praveenjuge/teak/main/.claude/agents/files-worker.md
Clone the repo
git clone --depth 1 https://github.com/praveenjuge/teak

Made for: Claude Code.

Wrote 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.

agentmods badge for files-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/praveenjuge/teak/files-worker/github.svg)](https://agentmods.dev/agents/praveenjuge/teak/files-worker)
Your own site
<a href="https://agentmods.dev/agents/praveenjuge/teak/files-worker"><img src="https://agentmods.dev/badge/agents/praveenjuge/teak/files-worker/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.

agentmods 80×15 button for files-worker

Your own site · 80×15
<a href="https://agentmods.dev/agents/praveenjuge/teak/files-worker"><img src="https://agentmods.dev/badge/agents/praveenjuge/teak/files-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 516 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.00516
Opus 5.5 $0.00028 $0.00206
Sonnet 5.5 $0.00014 $0.00103
Haiku 4.5 $0.00007 $0.00052

Measured 2d ago against content hash b862cd899874, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

files-worker 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 2d 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.

.claude/agents/files-worker.md · 23 lines

What it actually says

You work on Teak's Cloudflare Workers. Before changing anything, read apps/files-worker/README.md (the sections the task touches) and the root AGENTS.md architecture invariants. Load the wrangler, workers-best-practices and durable-objects skills when the task needs them; retrieve current Cloudflare docs instead of relying on memory.

Invariants to keep:

  • Workflow step names are durable history: never rename one, and add new steps after the existing ones.
  • Every card-processing write carries the run's processing revision (guardOf(job)); a stale write must end the run as skipped, never overwrite newer work. Keep processingStatus consistent and every run reporting back through workflowDispatch.complete.
  • A NonRetryableError thrown inside a step reaches the workflow as a plain Error whose message starts with NonRetryableError: . Code that matches on a step error's message must allow for that prefix.
  • Development binds only development resources (development/wrangler.jsonc); never point it at production buckets, indexes, routes or secrets.
  • After changing a Wrangler config, run bun run cf-typegen in apps/files-worker; never hand-edit worker-configuration.d.ts.

Prove the change, cheapest first:

  1. bun test <file> in apps/files-worker, then bun run test and bun run typecheck there, and bun run cf-typegen:check.
  2. When the behavior depends on the real Workflows engine (retries, errors crossing a step, completion reports), add a case to src/workflows/cardProcessing/engine.test.ts (Wrangler's createTestHarness, no account needed).
  3. For user-visible behavior, follow .agents/skills/verify-teak/features/card-processing.md: run the local E2E stack and read the run's steps, logs and stored objects through Local Explorer.

Report what changed, the commands you ran with their results, and anything you could not reach (for example Containers without a running Docker daemon, or remote bindings without a Cloudflare token).

Changes

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.

  1. 2d ago First seen · 23 lines · 70 tokens per session scan A b862cd899874

Subscribe to this mod's changes

files-worker is an agent published in the GitHub repository praveenjuge/teak (25 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 516 once invoked, about $0.0003 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 2026-10-20.

Related

Other agents, from other repositories

service-mesh-expert

Expert service mesh architect specializing in Istio, Linkerd, and cloud-native networking patterns. Masters traffic management, security policies, observability integration, and multi-cluster mesh configurations. Use PROACTIVELY for service mesh architecture, zero-trust networking, or microservices communication…

wshobson/agents · 63 tokens

serv

Designs serverless architectures for Lambda, Cloud Functions, and Cloud Run — cold start mitigation, event-driven wiring, cost modeling, and IaC via SAM or Serverless Framework. Use when building or auditing serverless workloads. Trigger with "design a serverless architecture", "optimize my Lambda cold starts".

jeremylongshore/tons-of-skills-marketplace · 64 tokens

gcp-cloud-architect

GCP cloud architect specializing in designing and implementing scalable Google Cloud solutions. Expert in GCE, GKE, Cloud Run, App Engine, and GCP best practices for containerized and serverless deployments.

andisab/swe-marketplace · 47 tokens

drupal-ddev

Use this agent for managing DDEV-based Drupal 11 projects — installing/updating modules, running Drush commands, managing configuration, database operations, cache management, and Composer workflows.

siva01c/claude-plugins · 41 tokens

hono-builder

Expert Hono developer for implementing routes, middleware, handlers, and integrations with Cloudflare Workers bindings.

smicolon/ai-kit · 24 tokens

integration-engineer

Integration engineer. Connects the chatbot to messaging channels (Slack, KakaoTalk, web) and implements integration with external APIs and databases. Responsible for deployment and infrastructure.

revfactory/harness-100 · 38 tokens