divine-mobile: Skill for Claude Code

.agents/skills/local-cache-idempotency-fallback/SKILL.md

local-cache-idempotency-fallback is a skill for Claude Code, Codex from divinevideo/divine-mobile. It costs 89 tokens per session (982 once invoked), scanned A, original, MPL-2.0.

A database-backed pattern for keeping stable results when an external API does not reliably return the same resource for the same request. The database stores and reuses identifiers from earlier runs.

In plain words
What is it for?
Use it for integrations that create users or other resources through external APIs and need stable IDs, public keys, tokens, or other saved values across runs.
Why use it?
It prevents rerunning a script from creating duplicates or changing identifiers when the external service's promised idempotency fails. Idempotency means repeating an operation should have the same effect as doing it once.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents).

This is divinevideo/divine-mobile's own configuration. It tells Claude Code and Codex how to work on divine-mobile 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 divine-mobile configures →

Reuse

Borrowing it

Nothing to install: this file belongs to divinevideo/divine-mobile. 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/divinevideo/divine-mobile/main/.agents/skills/local-cache-idempotency-fallback/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/divinevideo/divine-mobile

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.

agentmods badge for local-cache-idempotency-fallback

README.md
[![agentmods](https://agentmods.dev/badge/skills/divinevideo/divine-mobile/local-cache-idempotency-fallback.svg)](https://agentmods.dev/skills/divinevideo/divine-mobile/local-cache-idempotency-fallback)
Your own site
<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/local-cache-idempotency-fallback"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/local-cache-idempotency-fallback.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 982 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00089 $0.00982
Opus 5 $0.00044 $0.00491
Sonnet 5 $0.00018 $0.00196
Haiku 4.5 $0.00009 $0.00098

Measured 4d ago against content hash f63336a19284, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

local-cache-idempotency-fallback 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 4d 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.

.agents/skills/local-cache-idempotency-fallback/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local Cache as Idempotency Fallback

Problem

External APIs that should be idempotent (same input = same output) sometimes aren't. This causes problems when re-running scripts:

  • Duplicate resources created
  • Identifiers change between runs
  • State becomes inconsistent across systems

Context / Trigger Conditions

  • Re-running a script creates new resources instead of finding existing ones
  • External API "fixed" idempotency but still returns different values
  • Need stable identifiers (pubkeys, user IDs, resource IDs) across runs
  • Script works once but fails on subsequent runs due to changed IDs

Solution

Use database cache as the source of truth for idempotency:

// BEFORE: Always calls external API (brittle)
const { pubkey, token } = await externalApi.createUser(userId, username);
await db.saveUser({ userId, pubkey, token });

// AFTER: Check cache first (robust)
const cached = await db.getUser(userId);
let pubkey: string;
let token: string;

if (cached) {
  // Use cached values - stable across runs
  pubkey = cached.pubkey;
  token = cached.token;
  console.log(`Using cached pubkey: ${pubkey}`);
} else {
  // Only call external API for genuinely new items
  const result = await externalApi.createUser(userId, username);
  pubkey = result.pubkey;
  token = result.token;

  // Cache immediately for next run
  await db.saveUser({ userId, pubkey, token });
  console.log(`Created new pubkey: ${pubkey}`);
}

Key Pattern

  1. Check local first: Always query your database before calling external API
  2. Use cached values: If found, use local values even if stale
  3. Only create when missing: External API called only for genuinely new items
  4. Cache immediately: Save result right after successful API call
  5. Log the source: Indicate whether value is "(cached)" or "(new)" for debugging

Verification

  • Re-run script multiple times
  • Same identifier used each time (from cache)
  • No duplicate resources created in external system
  • Script is idempotent regardless of external API behavior

Read the full file on GitHub · 131 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. 4d ago First seen · 131 lines · 89 tokens per session scan A f63336a19284

Subscribe to this mod's changes

local-cache-idempotency-fallback is a skill published in the GitHub repository divinevideo/divine-mobile (265 stars, last pushed today), licensed MPL-2.0. It adds 89 tokens to every session and 982 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 2026-09-03.

Related

Other skills, from other repositories

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

wshobson/agents · 33 tokens

convex-explain-app

Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.

openclaw/clawhub · 47 tokens

platform-custom-field-generate

Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…

forcedotcom/sf-skills · 194 tokens

openloomi-api

OpenLoomi ships a local-first HTTP API served from the desktop app (port 3414, fallback 3515). All auth, Memory, AI, RAG, Loop, and Audit data live in a local SQLite database — your data stays on your machine and the OpenLoomi app is the source of truth. The only externally-routed auth path is the Composio OAuth…

melandlabs/openloomi · 106 tokens

nornicdb-grpc

Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…

orneryd/NornicDB · 98 tokens

field-service-sobject-create-configure

Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…

forcedotcom/sf-skills · 74 tokens