openstory: Instructions file for Claude Code

CLAUDE.md

openstory CLAUDE.md is an instructions file for Claude Code from openstory-so/openstory. It costs 15,544 tokens per session, scanned A, original, MIT.

A monitoring guide for building and operating observability on Amazon Web Services (AWS), including logs, measurements, alerts, dashboards, and request tracing.

In plain words
What is it for?
Use it when configuring CloudWatch metrics and logs, alarms, Logs Insights queries, dashboards, X-Ray tracing, or anomaly detection.
Why use it?
It helps teams find missing monitoring, understand system behavior, and investigate problems in AWS services.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument.

This is openstory-so/openstory's own configuration. It tells Claude Code how to work on openstory 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 openstory configures →

Reuse

Borrowing it

Nothing to install: this file belongs to openstory-so/openstory. 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/openstory-so/openstory/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/openstory-so/openstory

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 openstory CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/openstory-so/openstory/claude-md/github.svg)](https://agentmods.dev/instructions/openstory-so/openstory/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/openstory-so/openstory/claude-md"><img src="https://agentmods.dev/badge/instructions/openstory-so/openstory/claude-md/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 openstory CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/openstory-so/openstory/claude-md"><img src="https://agentmods.dev/badge/instructions/openstory-so/openstory/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15,544 This file is loaded in full into every session.
When invoked 15,544 The same file — it is already loaded in full.
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 $0.15544 $0.15544
Opus 5 $0.07772 $0.07772
Sonnet 5 $0.03109 $0.03109
Haiku 4.5 $0.01554 $0.01554

Measured today against content hash 08729890002d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

openstory CLAUDE.md 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 today.

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.md · 738 lines

How it starts

The opening of the file, as written. The whole thing — 738 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

AI-powered video sequence platform built with TanStack Start, deployed to Cloudflare Workers.

Commands

# Dev
bun dev                            # App: env bootstrap, DB migrate + seed, Vite (Workerd via cf-plugin)
bun dev:all                        # bun dev + the Stripe listener (billing webhooks)
bun storybook                      # Storybook on :6006
bun explorer                       # Open the local CF Explorer (KV/R2/D1/DOs/Workflows)
bun db:studio:local                # Inspect local D1 tables (wrangler d1 execute)

# Quality
bun lint                           # oxlint (type-aware)
bun lint:fix
bun format                         # oxfmt
bun format:check
bun typecheck                      # tsgo --noEmit (NOT `tsc`)
bun dead-code                      # knip (unused exports)

# Tests
bun run test                       # unit (Vitest) — NOT `bun test` (that invokes Bun's built-in test runner)
bun run test src/path/foo.test.ts  # single file
bun run test:watch
bun run test:coverage
bun test:e2e                       # Playwright (vite dev cf-plugin webServer)
bun test:e2e:ui
bun test:e2e:setup                 # apply D1 migrations + seed for [env.test]
bun test:e2e:full                  # full-pipeline e2e (Cloudflare Workflows + aimock)
bun run build:e2e                  # built-server e2e build (VITE_APP_URL=:3001, devtools off)

# DB (Wrangler local D1 via Miniflare)
bun db:migrate:local               # drizzle-orm migrator against local D1 (default env)
bun db:migrate:test                # drizzle-orm migrator against local D1 ([env.test])
bun db:migrate:prd                 # flatten + wrangler d1 migrations apply DB --env=production --remote
bun db:seed:local                  # seed local D1 via getPlatformProxy
bun db:generate                    # generate migration from schema edits
bun db:studio:d1                   # Drizzle Studio against production D1

# Build / deploy
bun run build                      # Vite production build (NOT `bun build`)
bun cf:dev                         # wrangler dev against built worker (preview)
bun cf:deploy:prd                  # Manual production deploy (build → migrate → deploy)
bun run deploy                     # Deploy-button deploy command (migrate + deploy, default env)
bun deploy:production              # Workers Builds prod deploy command (migrate --env=production + deploy)

Read the full file on GitHub · 738 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.

  1. today Changed · +40 lines · +1,241 tokens per session 08729890002d
  2. yesterday Changed · +3 lines · +647 tokens per session c125f0081c73
  3. 2d ago Changed · +2 lines · +413 tokens per session 30d2d8ba3da0
  4. 4d ago Changed · +51 lines · +1,499 tokens per session bf7c7e46e155
  5. 5d ago Changed · +138 lines · +2,533 tokens per session 271989ed7073
  6. 10d ago First seen · 504 lines · 9,211 tokens per session scan A 5f0244b28a38

Subscribe to this mod's changes

openstory CLAUDE.md is an instructions file published in the GitHub repository openstory-so/openstory (607 stars, last pushed today), licensed MIT. It adds 15,544 tokens to every session, about $0.0777 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 2026-08-30.

Related

Other instructions, from other repositories