Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add divinevideo/divine-mobile --skill stale-cache-external-service-recoverygit clone --depth 1 https://github.com/divinevideo/divine-mobileWrote 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.
[](https://agentmods.dev/skills/divinevideo/divine-mobile/stale-cache-external-service-recovery)<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/stale-cache-external-service-recovery"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/stale-cache-external-service-recovery/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.
<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/stale-cache-external-service-recovery"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/stale-cache-external-service-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00111 | $0.01305 |
| Opus 5.5 | $0.00044 | $0.00522 |
| Sonnet 5.5 | $0.00022 | $0.00261 |
| Haiku 4.5 | $0.00011 | $0.00130 |
Grade A, and why
stale-cache-external-service-recovery 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stale Cache Recovery When External Service Loses Data
Problem
When using your database as a cache/idempotency layer (see local-cache-idempotency-fallback),
a new failure mode emerges: the external service loses or resets its data, but your
cache still has the old values. Operations fail with misleading errors because the cached
identifiers don't exist on the external service anymore.
Context / Trigger Conditions
- Token refresh fails with 404 "User with pubkey/id not found"
- Operations fail with "Invalid or expired token" but the real issue is missing user
- External service was reset, migrated, or lost data
- Cached identifiers (pubkeys, API keys, user IDs) are valid in cache but not on service
- Error message is misleading - suggests token issue when it's actually a missing resource
Solution
Detect the specific "not found" case and handle it separately from other errors:
if (cached) {
pubkey = cached.pubkey;
token = cached.token;
try {
// Try to refresh/validate the cached credentials
const freshToken = await externalApi.getTokenByPubkey(pubkey);
token = freshToken;
console.log(`Pubkey: ${pubkey} (token refreshed)`);
} catch (error) {
const errMsg = error instanceof Error ? error.message : String(error);
// CRITICAL: Detect "not found" specifically - cache is stale
if (errMsg.includes("not found") || response.status === 404) {
console.log(`Cached identifier not on external service, recreating...`);
// 1. Delete stale cache entry
await db.deleteUser(userId);
// 2. Create fresh resource on external service
const result = await externalApi.createUser(userId, username);
pubkey = result.pubkey;
token = result.token;
console.log(`Pubkey: ${pubkey} (recreated)`);
// 3. Cache new values
await db.saveUser({ userId, pubkey, token });
} else {
// Other error (e.g., user claimed account, rate limit) - can't proceed
console.log(`Refresh failed: ${errMsg}`);
continue; // or throw
}
}
}
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.
- 1mo ago First seen · 159 lines · 111 tokens per session scan A b72858fa2bca
stale-cache-external-service-recovery is a skill published in the GitHub repository divinevideo/divine-mobile (264 stars, last pushed today), licensed MPL-2.0. It adds 111 tokens to every session and 1,305 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
convex-insights
Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
platform-apex-anonymous-run
Runs anonymous Apex against the connected org (.apex file or pasted snippet), capturing the debug log, surfacing errors. Triggers on "run this anonymous apex", "execute this script against my org", "what does this code return", or "execute scripts/foo.apex". Wraps scripts in savepoint+rollback; warns before running in…