Prompt Caching
davila7/claude-code-templates
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache…
Attempt formal correctness proofs for all public cache methods
Apache-2.0Auto-check passed
Install Audit Correctness Proof
$ npx skills add ben-manes/caffeine --skill audit-correctness-proof -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ben-manes/caffeine audit-correctness-proof --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ben-manes/caffeine.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/audit-correctness-proof .claude/skills/audit-correctness-proof && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "audit-correctness-proof" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-correctness-proof into .claude/skills/audit-correctness-proof/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-correctness-proof", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-correctness-proofType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ben-manes/caffeine --skill audit-correctness-proof -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ben-manes/caffeine audit-correctness-proof --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ben-manes/caffeine.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/audit-correctness-proof .agents/skills/audit-correctness-proof && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "audit-correctness-proof" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-correctness-proof into .agents/skills/audit-correctness-proof/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-correctness-proof", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ben-manes/caffeine --skill audit-correctness-proof -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ben-manes/caffeine audit-correctness-proof --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ben-manes/caffeine.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/audit-correctness-proof .cursor/skills/audit-correctness-proof && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "audit-correctness-proof" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-correctness-proof into .cursor/skills/audit-correctness-proof/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-correctness-proof", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ben-manes/caffeine.git --path .claude/skills/audit-correctness-proof--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ben-manes/caffeine --skill audit-correctness-proof -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ben-manes/caffeine audit-correctness-proof --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ben-manes/caffeine.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/audit-correctness-proof .gemini/skills/audit-correctness-proof && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "audit-correctness-proof" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-correctness-proof into .gemini/skills/audit-correctness-proof/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-correctness-proof", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ben-manes/caffeine audit-correctness-proofInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ben-manes/caffeine --skill audit-correctness-proof -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ben-manes/caffeine.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/audit-correctness-proof .github/skills/audit-correctness-proof && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "audit-correctness-proof" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-correctness-proof into .github/skills/audit-correctness-proof/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-correctness-proof", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ben-manes/caffeine --skill audit-correctness-proof -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ben-manes/caffeine audit-correctness-proof --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ben-manes/caffeine.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/audit-correctness-proof .opencode/skills/audit-correctness-proof && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "audit-correctness-proof" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-correctness-proof into .opencode/skills/audit-correctness-proof/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-correctness-proof", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
audit-correctness-proof- GitHub stars
- 18k
- Token cost
- ~275 tokens
- SKILL.md length
- 134 words
- Files
- 1
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Attempt formal correctness proofs for all public cache methods
- Works in 4 steps: State the method's specification:… → Identify the synchronization protocol… → Write a proof sketch → …
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Audit Correctness Proof is an agent skill from ben-manes/caffeine. Attempt formal correctness proofs for all public cache methods
Its SKILL.md is about 280 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: A high performance caching library for Java. The licence is Apache-2.0.
Example prompts
- “/audit-correctness-proof”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- State the method's specification: preconditions, postconditions,
- Identify the synchronization protocol ensuring the postcondition.
- Write a proof sketch
- If you CANNOT complete the proof at any step, stop and report
What it can do on your machine
Read from SKILL.md and the folder at commit e972fb0. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Audit Correctness Proof loads about 275 tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 134 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from ben-manes/caffeine at commit e972fb0, republished under its Apache-2.0 licence (© ben-manes). 134 words, ~275 tokens.
Download SKILL.mdSave it as
.claude/skills/audit-correctness-proof/SKILL.md (or your agent's skills folder).- name
- audit-correctness-proof
- description
- Attempt formal correctness proofs for all public cache methods
- context
- fork
- agent
- auditor
- disable-model-invocation
- true
Attempt to PROVE the correctness of the cache, not to find bugs.
For each public method (get, put, remove, compute, computeIfAbsent, merge, replace, size, clear):
State the method's specification: preconditions, postconditions, concurrent behavior promises.
Identify the synchronization protocol ensuring the postcondition.
Write a proof sketch: a. Assume the precondition holds b. Identify the critical section(s) c. Show the postcondition is established within the critical section d. Show no concurrent operation can invalidate it before the caller observes
If you CANNOT complete the proof at any step, stop and report:
- Which step fails
- What additional assumption would be needed
- Whether the code guarantees that assumption
Gaps in the proof are more valuable than speculative bug reports — a gap tells us exactly where to look.
Do not provide praise or style commentary.
© ben-manes, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/audit-correctness-proof of ben-manes/caffeine.
Open the folder on GitHubat commit e972fb0
Compare with similar skills
Audit Correctness Proof next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Audit Correctness Proof this skillben-manes/caffeine | 18k | — | ~275 | Automated safety check: Pass | Apache-2.0 | |
| Prompt Cachingdavila7/claude-code-templates | 32k | 6 repos | ~452 | Automated safety check: Pass | MIT | |
| Turborepo Cachingwshobson/agents | 40k | 9 repos | ~2k | Automated safety check: Notes | MIT | |
| OmniRoute LLM Cachediegosouzapw/OmniRoute | 74k | 1 repos | ~529 | Automated safety check: Pass | MIT | |
| Cachingzebbern/claude-code-guide | 4.7k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Content-Hash File Cache Patternaffaan-m/ECC | 275k | 5 repos | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
Turborepo Caching
wshobson/agents
Configures Turborepo pipelines and local or remote caching for monorepo builds, including Vercel remote cache, a self-hosted cache and cache-miss debugging.
OmniRoute LLM Cache
diegosouzapw/OmniRoute
Documents OmniRoute's cache endpoints for reading cache statistics and clearing entries, statistics or the reasoning cache, with notes on TTL and similarity settings.
Caching
zebbern/claude-code-guide
Caching strategies — invalidation, TTL guidelines, cache keys, cache layers, and when not to cache.
Content-Hash File Cache Pattern
affaan-m/ECC
Caches slow file processing results in Python keyed by a SHA-256 hash of the file content, so renames still hit the cache and edits invalidate it automatically.
Browser Caching
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Enable browser caching.
More from ben-manes/caffeine
All 33 skills in this repoCaffeine Cache Optimization Experiments
ben-manes/caffeine
Runs controlled JMH experiments on the Caffeine cache to find shared contention and hot-path waste, then reviews correctness and returns a reviewable patch.
Git History Bug Audit
ben-manes/caffeine
Audits a module by walking its git history commit by commit, tracking unresolved issues forward, and reporting the ones that survive to HEAD as findings.
Adversarial Codebase Audit
ben-manes/caffeine
Runs a hostile review of the Caffeine Java caching library with parallel subagents that get no design docs, then challenges and consolidates their findings.
Caffeine Performance Audit
ben-manes/caffeine
Audits the Caffeine cache source for hot-path costs such as allocations, contention and memory layout, reporting only findings tied to specific lines.
Audit Sibling Divergence
ben-manes/caffeine
Compares code paths that should behave the same, such as sync and async cache methods, and requires a concrete scenario where the two observably disagree.
Climber Step Minimization
ben-manes/caffeine
Prices each step of the window climber algorithm by disabling it in turn, to find steps that no longer earn their keep and branches that no longer fire.
Questions about Audit Correctness Proof
What does Audit Correctness Proof do?
Attempt formal correctness proofs for all public cache methods. Audit Correctness Proof is an agent skill from ben-manes/caffeine.
How do I install Audit Correctness Proof in Claude Code?
Run `npx skills add ben-manes/caffeine --skill audit-correctness-proof -a claude-code`. Or copy the skill folder (.claude/skills/audit-correctness-proof in ben-manes/caffeine) into .claude/skills/audit-correctness-proof in your project. Claude Code loads it when a task matches its description.
How do I install Audit Correctness Proof in Codex?
Run `npx skills add ben-manes/caffeine --skill audit-correctness-proof -a codex`. Or copy the skill folder (.claude/skills/audit-correctness-proof in ben-manes/caffeine) into .agents/skills/audit-correctness-proof in your project. Codex loads it when a task matches its description.
Can I use Audit Correctness Proof in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ben-manes/caffeine --skill audit-correctness-proof -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-correctness-proof, .gemini/skills/audit-correctness-proof, .github/skills/audit-correctness-proof and .opencode/skills/audit-correctness-proof in your project.
What does Audit Correctness Proof need to run?
SKILL.md names no scripts, command-line tools or credentials: Audit Correctness Proof is instructions for the agent only.
Does Audit Correctness Proof access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Audit Correctness Proof safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Audit Correctness Proof use?
Audit Correctness Proof is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Audit Correctness Proof use?
About 275 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Audit Correctness Proof?
Skills that share tags, products or a category with Audit Correctness Proof: Prompt Caching (davila7/claude-code-templates, 32k stars), Turborepo Caching (wshobson/agents, 40k stars), OmniRoute LLM Cache (diegosouzapw/OmniRoute, 74k stars) and Caching (zebbern/claude-code-guide, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Audit Correctness Proof?
ben-manes (a GitHub user) maintains it in ben-manes/caffeine, which has 17,880 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 6, 2026.
Source: ben-manes/caffeine on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.