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.
git clone --depth 1 https://github.com/pruthvinathJV/nextjs-claude-code-kitWrote 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/commands/pruthvinathjv/nextjs-claude-code-kit/check-cache)<a href="https://agentmods.dev/commands/pruthvinathjv/nextjs-claude-code-kit/check-cache"><img src="https://agentmods.dev/badge/commands/pruthvinathjv/nextjs-claude-code-kit/check-cache/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/commands/pruthvinathjv/nextjs-claude-code-kit/check-cache"><img src="https://agentmods.dev/badge/commands/pruthvinathjv/nextjs-claude-code-kit/check-cache.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00617 |
| Opus 5.5 | $0.00000 | $0.00247 |
| Sonnet 5.5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
check-cache 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.
What it actually says
Audit caching configuration in $ARGUMENTS for Next.js 15 correctness.
This project uses Next.js 15, where the default fetch cache behavior is no-store (no cache).
Pre-Next.js 15 defaults (force-cache) are incorrect unless explicitly intentional.
Scan for these patterns:
-
fetchcalls without explicit cache option- In Next.js 15 these default to no-store, which is correct
- Flag if the data looks like it should be cached (static content, rarely-changing data)
- Suggest adding
{ next: { revalidate: N } }if appropriate
-
{ cache: 'force-cache' }usage- Flag every instance — this was the pre-15 default but is now an explicit choice
- Verify it's intentional: is this data truly static and safe to cache indefinitely?
- If not, replace with
{ next: { revalidate: N } }with an appropriate revalidation period
-
export const revalidateat segment level- Check the value is intentional and matches the data freshness requirements
- Flag
export const revalidate = false(cache forever) — usually too aggressive
-
Missing
revalidatePathorrevalidateTagafter mutations- Check Server Actions that mutate data
- If no revalidation call exists after a write, the UI may show stale data indefinitely
- Suggest appropriate revalidation based on what was mutated
-
export const dynamic = 'force-static'with dynamic data- Flag if the route fetches user-specific or frequently-changing data while forced static
-
GETRoute Handlers without explicit caching config- In Next.js 15,
GETRoute Handlers are no longer cached by default - If a Route Handler returns data that should be cached (e.g., a product list, static config), flag the missing
export const dynamic = 'force-static'orexport const revalidate = N - Do NOT flag handlers that return dynamic/user-specific data — uncached is correct there
- In Next.js 15,
Output format: For each file with caching issues:
app/products/page.tsx
Line 12: fetch('/api/products', { cache: 'force-cache' })
⚠️ force-cache is now explicit in Next.js 15. Is this data truly static?
Suggestion: { next: { revalidate: 3600 } } if it changes hourly, or keep force-cache if truly static
app/actions/updateCart.ts
Line 8: await db.cart.update(...)
❌ No revalidatePath() call after mutation
Suggestion: Add revalidatePath('/cart') after the update
End with a caching strategy summary: how many routes are uncached, how many are force-cached, how many use time-based revalidation, and whether the overall strategy looks coherent.
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 · 50 lines · 0 tokens per session scan A 0706ced1e693
check-cache is a command published in the GitHub repository pruthvinathJV/nextjs-claude-code-kit (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 617 tokens. 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 2026-08-31.
Other commands, from other repositories
fix-issue
Investigate and fix an issue.
debug
Debug code issues with systematic problem-solving and troubleshooting steps.
umt-doctor
Diagnose UMT MCP server setup — builds, environment variables, and config health.
techdebt-scan
Scan a project directory for technical debt across all supported languages and print a prioritized summary of findings.
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
type-coverage
Vérification Couverture des Types Python.