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 Stijnman/grok-custom-skills --skill predictive-cache-managergit clone --depth 1 https://github.com/Stijnman/grok-custom-skillsWrote 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/stijnman/grok-custom-skills/predictive-cache-manager)<a href="https://agentmods.dev/skills/stijnman/grok-custom-skills/predictive-cache-manager"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/predictive-cache-manager/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/stijnman/grok-custom-skills/predictive-cache-manager"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/predictive-cache-manager.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 | $0.00033 | $0.00299 |
| Opus 5 | $0.00016 | $0.00150 |
| Sonnet 5 | $0.00007 | $0.00060 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
predictive-cache-manager 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 9d 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
Predictive Cache Manager
When to Use
- User says cache results or task matches this capability
- User says prefetch or task matches this capability
- User says reuse cache or task matches this capability
- User says avoid repeat fetch or task matches this capability
Workflow
- Identify repeat queries from session history.
- Cache with TTL based on data freshness needs.
- Invalidate on write operations to same resource.
- Prefetch only high-confidence next steps.
Integrations
performance-optimizermega-context-manager
Error Handling
| Failure | Response |
|---|---|
| Stale cache served | Shorten TTL; add freshness check. |
Gotchas
- Never cache auth tokens or PII.
Example
Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.
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.
- 9d ago First seen · 47 lines · 33 tokens per session scan A 1010283d1f2d
predictive-cache-manager is a skill published in the GitHub repository Stijnman/grok-custom-skills (9 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 299 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
remote-compute-ops
Operate GPU and remote compute across RunPod (Pods and Serverless), Massed Compute VMs, and owned or virtual remote servers through existing bridges, SSH sessions, MCP/API adapters, bounded polling, cost controls, and resumable lifecycle checks. Use when the user mentions RunPod, Massed Compute, a remote…
alterlab-remote-compute
Dispatch long-running GPU/CPU jobs to remote compute with a provider-agnostic submit → poll → harvest pattern across SLURM/HPC (sbatch, squeue, sacct) and managed APIs (Modal, RunPod, GCP Batch / Vertex AI). Use when submitting a batch job to a cluster, polling job status, retrieving result artifacts from a scheduler…
goal-meta-skill
A guide for turning an unclear or complex task into a reviewable /goal instruction for coding agents.
aws-api-mcp
Comprehensive AWS API support with command validation and access to all services.
aws-appsync-mcp
Manage applications powered by AWS AppSync.
aws-bedrock-custom-model-import-mcp
Manage custom models in Bedrock.