What is teak-core-worker?

A set of instructions for changing and debugging Teak's Cloudflare Worker, the server-side program that runs on Cloudflare's network. It covers card processing, storage, queues, workflows, and the edge API proxy.

Use it when changing the Core Worker, Wrangler configuration, card imports or exports, deletion runs, Cloudflare storage, queues, durable objects, or related API and MCP proxy code.

It helps prevent changes that break stored workflow history, overwrite newer processing results, or connect development code to production resources. It also points the agent to the repository rules and required checks.

How praveenjuge/teak configures Claude Code and Codex

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/.agents/skills/teak-core-worker/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/praveenjuge/teak

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/praveenjuge/teak/teak-core-worker/github.svg)](https://agentmods.dev/skills/praveenjuge/teak/teak-core-worker)

Your own site

<a href="https://agentmods.dev/skills/praveenjuge/teak/teak-core-worker"><img src="https://agentmods.dev/badge/skills/praveenjuge/teak/teak-core-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/praveenjuge/teak/teak-core-worker"><img src="https://agentmods.dev/badge/skills/praveenjuge/teak/teak-core-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 594 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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.00594
Opus 5.5	$0.00028	$0.00238
Sonnet 5.5	$0.00014	$0.00119
Haiku 4.5	$0.00007	$0.00059

Measured yesterday against content hash dd7b00498986, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

teak-core-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 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.

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.

.agents/skills/teak-core-worker/SKILL.md · 26 lines

How it starts

The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teak Core Worker

Before changing anything, read the sections of apps/core-worker/README.md the task touches and "Rules every change keeps" in apps/docs/content/docs/(open-source)/architecture.mdx. Load the wrangler, workers-best-practices and durable-objects skills when the task needs them, and read current Cloudflare docs instead of relying on memory.

Invariants

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 ends the run as skipped and never overwrites 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 (apps/core-worker/development/wrangler.jsonc); never point it at production buckets, indexes, routes or secrets.
Self-hosted deployments use apps/core-worker/self-host/wrangler.jsonc. A binding, queue, cron, limit or container added to wrangler.jsonc goes there too in the same change (src/deployment.test.ts fails otherwise); never put an account, route, resource ID or Teak value in it.
After changing a Wrangler config, run bun run cf-typegen in apps/core-worker; never hand-edit worker-configuration.d.ts.

Prove the change, cheapest first

bun test <file> in apps/core-worker, then bun run test and bun run typecheck there, and bun run cf-typegen:check.
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).
For user-visible behavior, follow .agents/skills/verify-teak/features/card-processing.md: run the local end-to-end stack and read the run's steps, logs and stored objects through Local Explorer.

Read the full file on GitHub · 26 lines

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.

yesterday Changed · +1 lines dd7b00498986
6d ago First seen · 25 lines · 71 tokens per session scan A 7d5227f27d9b

Subscribe to this mod's changes

teak-core-worker is a skill published in the GitHub repository praveenjuge/teak (24 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 594 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 2026-11-01.

Backend and APIs Cloud DevOps and cloud bookmark-manager browser-extension electron expo knowledge-base mcp

teak-core-worker next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
teak-core-workerpraveenjuge/teak	Skill	24	yesterday	MIT	A	71	Claude Code, Codex
sse-streamingfabioc-aloha/Alex_Skill_Mall	Skill	5	today	MIT	A	26	Claude Code, Codex
consul-knowledge-patchNevaberry/nevaberry-plugins	Skill	26	2mo ago	MIT	A	12	Claude Code
edge-functionsAmpli-Group/agentic-mobile-blueprint	Skill	4	3mo ago	MIT	A	52	Claude Code, Codex
stripe-projectsNousResearch/hermes-agent	Skill	261k	yesterday	MIT	A	15	Claude Code, Codex
django-storages-s3Jeffallan/claude-skills	Skill	12k	7d ago	MIT	A	138	Claude Code
aws-blocksaws/agent-toolkit-for-aws	Skill	3.4k	yesterday	Apache-2.0	A	105	Claude Code

teak: Skill for Claude Code