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 IgorWarzocha/howaboua-pi-stuff --skill prompt-cachinggit clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuffWrote 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/igorwarzocha/howaboua-pi-stuff/prompt-caching)<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/prompt-caching"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/prompt-caching/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/igorwarzocha/howaboua-pi-stuff/prompt-caching"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/prompt-caching.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 | $0.00022 | $0.00681 |
| Opus 5.5 | $0.00009 | $0.00272 |
| Sonnet 5.5 | $0.00004 | $0.00136 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
prompt-caching 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use provider-reported cache reads and writes as evidence. Continuation IDs, prewarm readiness, predictions, keys, and latency do not prove a hit. Verify the active endpoint and usage mapping rather than assuming public-API parity.
Design for a small, stable static prefix before adding capabilities. Prefer code-mode or deferred tool discovery over loading every schema upfront. Keep available capabilities discoverable while revealing their current arguments on demand. Supply tool-specific instructions through supported mid-session system or developer messages, help, or tool results instead of rewriting the prefix. Do not preload instructions merely because a tool may become relevant later.
Locate the first unexplained miss
- For a reported miss, start with the transition and adjacent provider calls, not an aggregate hit ratio. Expand lifecycle coverage when shared state or an explicit audit requires it. An agent turn may contain several requests. Mark deliberate model, reasoning, mode, prompt, tool, compaction, and history boundaries first.
- Compare final provider requests in order: system and developer instructions, ordered tool contracts, ordered input items and their identities, structured-output definitions, then lane and continuation properties. Session logs and source strings are not the wire payload.
- Trace the first divergence backwards through the actual preparation and rewrite chain. Identify the owner and capture event of each consumed snapshot, its completed hooks, lane, consumers, and invalidators. Correct bytes captured before authoritative preparation are stale. Use the latest completed final request in the same lane, not session-start state. Guard against late asynchronous work overwriting a newer lane.
- Adding context and starting a prepared run are different operations. Verify hook coverage for the implicated kickoff and queued paths. An idle check is not a reservation. Use an atomic route or revalidate at invocation.
- Prove the local mechanism in isolation, then exercise the affected multi-turn boundary in the user's complete extension setup. A later extension may change the same prompt, tools, or history.
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 Changed · +2 lines d80a3a03f652
- 1mo ago Changed · -72 lines 752bb1311c38
- 2mo ago First seen · 97 lines · 22 tokens per session scan A d88fc770dfa9
prompt-caching is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (413 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 681 once invoked, about $0.0001 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 2026-08-30.
prompt-caching compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prompt-cachingIgorWarzocha/howaboua-pi-stuff | Skill | 413 | yesterday | MIT | A | 22 | Claude Code, Codex |
| llm-app-patternsdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 54 | Claude Code, Codex |
| prompt-engineerJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 93 | Claude Code |
| prompt-optimizationlangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 105 | Claude Code, Codex |
| omh-model-optimizationrlaope/oh-my-hermes | Skill | 5.2k | today | MIT | A | 84 | Claude Code, Codex |
| ideogram4digitalsamba/claude-code-video-toolkit | Skill | 2.5k | today | MIT | A | 99 | Claude Code |
| prompt-library-for-startupsaws/agent-toolkit-for-aws | Skill | 3.4k | yesterday | Apache-2.0 | A | 228 | Claude Code |