Skip to main content
prompt CX Codex GP ChatGPT

cache-miss.sequence — Claude Code prompt: what it does, how to install

cache-miss.sequence drives the Archify skill to build a sequence diagram for a dashboard request that misses cache in Redis and falls through to PostgreSQL.

Apache-2.0 ★ 98,599 updated 2026-10-25

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/cache-miss.sequence.md
Open on GitHub

What cache-miss.sequence does

The prompt lays out a scenario where a browser hits an API, the API checks a JWT and reads Redis. On a cache miss, the API queries PostgreSQL for profile and metric data, writes the result back to Redis, emits a trace, and sends JSON back to the browser. The agent has to pick its own internal IDs and layout rather than reusing any example already checked into the repository.

The output is a typed JSON diagram specification built for the showcase quality profile, keeping message direction intact and separating calls, returns, security checks, and the asynchronous trace emission. When shell access is available, the agent runs the bundled Archify CLI to validate and repair the draft before freezing it; an external harness checks the frozen candidate independently.

The prompt requires writing the result to exactly benchmark-candidate.json in the repository root and touching no other file, since that file counts as the submission, not the chat reply. It also tells the agent not to claim validation passed.

What it helps with

  • model a request sequence that hits cache and falls through to a database
  • diagram a Redis cache-miss path into PostgreSQL
  • produce a typed diagram spec for the showcase quality profile
  • validate and repair a diagram draft with the Archify CLI
  • freeze a diagram candidate into a fixed file for external checking

Example prompts for the agent

  • Use the Archify skill to build a sequence diagram for a dashboard request with a Redis cache miss
  • Produce a showcase-profile JSON diagram spec and save it as benchmark-candidate.json
  • Run the Archify CLI to validate and repair the diagram candidate before writing the file

How to install cache-miss.sequence

Manually: put the files in place

.claude/commands/cache-miss.sequence.md

Questions about cache-miss.sequence

How do I install cache-miss.sequence in Claude Code?

Drop the prompt file at .claude/commands/cache-miss.sequence.md.

What does cache-miss.sequence do?

It directs the agent to use the Archify skill for drawing a sequence diagram of a dashboard request that checks a JWT, misses Redis cache, and queries PostgreSQL, then save the result to benchmark-candidate.json.

Why can't the agent reuse a checked-in example diagram?

The prompt explicitly forbids copying an existing example from the repository; the agent must generate its own IDs and layout or the submission does not count.

Source text

cache-miss.sequence.md · Apache-2.0
# Cache-miss request sequence

Use the Archify skill in this repository to create a sequence diagram for a dashboard request. A browser calls an API, the API validates the JWT, then reads Redis. Redis returns a cache miss, so the API queries PostgreSQL for profile and metric data, stores the result back in Redis, emits a trace, and returns JSON for the browser to render.

Author a fresh typed JSON diagram specification targeting the `showcase` quality profile. Choose your own stable internal IDs and layout. Preserve message direction and distinguish calls, returns, security checks, and asynchronous trace emission. Use the bundled Archify CLI to validate and repair the candidate when shell access is available. The external harness will independently validate the frozen candidate.

Write the final candidate to exactly `benchmark-candidate.json` in the repository root. Do not edit any other file. The candidate file, not the prose response, is the attempt 1 artifact. Do not copy a checked-in example. Do not claim that validation passed.

© tt-a1i · Apache-2.0 · tt-a1i/archify

Similar prompts

All prompts for Agent setup: memory, context, orchestration →

From the same set10

The whole set →
archify archify creates checked diagrams and one-page explainers as standalone HTML. Use it to show a system’s structure, data flow, or database schema. CX Codex +1 193,400installs web-runtime.architecture web-runtime.architecture — a prompt for generating a production web architecture JSON diagram using Archify and saving it directly to benchmark-candidate.json. CX Codex GP ChatGPT ★ 98,599repo stars product-analytics.dataflow This prompt guides Archify through a product analytics data-flow diagram, from web and mobile events to dashboards and a model, with a distinct path for consent-gated identity data. CX Codex GP ChatGPT ★ 98,599repo stars agent-tool-call.workflow agent-tool-call.workflow — a prompt for building a workflow diagram where an AI agent calls tools with human approval gates. CX Codex GP ChatGPT ★ 98,599repo stars agent-run.lifecycle agent-run.lifecycle instructs an agent to build a structured lifecycle diagram for an agent run using the Archify workflow. CX Codex GP ChatGPT ★ 98,599repo stars archify-review The archify-review skill weighs issues, pull requests, and code by value, cost, and impact. Use it for triage, change reviews, and maintenance decisions. CX Codex +1 ★ 98,599repo stars simplify-codebase simplify-codebase — a skill that audits a codebase for accidental complexity, then removes dead code, duplicated state or redundant layers once each cut is backed by evidence. CX Codex +1 ★ 98,599repo stars archify-tuning archify-tuning guides tuning and evaluation workflows for Archify diagram generation to improve visual layout and cut down repair cycles. CX Codex +1 ★ 98,599repo stars

More in the catalog

Project sponsors

Companies that keep this analytics open