Correct
cursor/plugins
Find the mistakes agents keep repeating in this repo and make each one impossible.
Audit serialization proxy correctness and round-trip safety. An agent skill from ben-manes/caffeine.
Apache-2.0Auto-check passed
Install Audit Serialization
$ npx skills add ben-manes/caffeine --skill audit-serialization -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ben-manes/caffeine audit-serialization --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-serialization .claude/skills/audit-serialization && 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-serialization" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-serialization into .claude/skills/audit-serialization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-serialization", 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-serializationType 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-serialization -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ben-manes/caffeine audit-serialization --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-serialization .agents/skills/audit-serialization && 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-serialization" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-serialization into .agents/skills/audit-serialization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-serialization", 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-serialization -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ben-manes/caffeine audit-serialization --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-serialization .cursor/skills/audit-serialization && 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-serialization" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-serialization into .cursor/skills/audit-serialization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-serialization", 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-serialization--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-serialization -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ben-manes/caffeine audit-serialization --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-serialization .gemini/skills/audit-serialization && 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-serialization" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-serialization into .gemini/skills/audit-serialization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-serialization", 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-serializationInstalls 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-serialization -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-serialization .github/skills/audit-serialization && 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-serialization" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-serialization into .github/skills/audit-serialization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-serialization", 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-serialization -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-serialization --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-serialization .opencode/skills/audit-serialization && 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-serialization" agent skill from https://github.com/ben-manes/caffeine/tree/master/.claude/skills/audit-serialization into .opencode/skills/audit-serialization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-serialization", 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-serialization- GitHub stars
- 18k
- Token cost
- ~364 tokens
- SKILL.md length
- 149 words
- Files
- 1
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Audit serialization proxy correctness and round-trip safety. An agent skill from ben-manes/caffeine.
- Works in 6 steps: Proxy completeness: Does the proxy… → State transfer: Are entries serialized… → Deserialized consistency: Correct… → …
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Audit Serialization is an agent skill from ben-manes/caffeine. Audit serialization proxy correctness and round-trip safety
Its SKILL.md is about 360 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-serialization”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Proxy completeness: Does the proxy capture ALL configuration?
- State transfer: Are entries serialized or only configuration?
- Deserialized consistency: Correct initial state for frequency sketch,
- Cross-version compatibility: serialVersionUID present? Can older
- Security: Can crafted serialized form create inconsistent state?
- Edge cases
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 Serialization loads about 364 tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 149 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). 149 words, ~364 tokens.
Download SKILL.mdSave it as
.claude/skills/audit-serialization/SKILL.md (or your agent's skills folder).- name
- audit-serialization
- description
- Audit serialization proxy correctness and round-trip safety
- context
- fork
- agent
- auditor
- disable-model-invocation
- true
Audit the serialization/deserialization behavior of the cache.
Proxy completeness: Does the proxy capture ALL configuration? Check: max size/weight, expiration, key/value strength, weigher, loader, removal/eviction listener, ticker, scheduler, executor, initial capacity.
State transfer: Are entries serialized or only configuration? If entries: are expired entries filtered? async values handled? weak/soft refs dereferenced? If not: is this documented?
Deserialized consistency: Correct initial state for frequency sketch, timer wheel, drain status, deques, weight counters? Correct node types?
Cross-version compatibility: serialVersionUID present? Can older proxies deserialize in newer versions? Default values correct for missing fields?
Security: Can crafted serialized form create inconsistent state? Are inputs validated? Is the proxy pattern correctly implemented?
Edge cases:
- Serializing during in-flight operations
- Serializing with pending removal notifications
- LoadingCache with non-serializable CacheLoader
- AsyncCache with incomplete futures
For each defect: state the field/behavior affected, before/after across round-trip, severity (data loss, incorrect behavior, security risk).
© 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-serialization of ben-manes/caffeine.
Open the folder on GitHubat commit e972fb0
Compare with similar skills
Audit Serialization 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 Serialization this skillben-manes/caffeine | 18k | — | ~364 | Automated safety check: Pass | Apache-2.0 | |
| Correctcursor/plugins | 10k | 3 repos | ~612 | Automated safety check: Pass | None | |
| Python Type Safetywshobson/agents | 40k | — | ~1.4k | Automated safety check: Pass | MIT | |
| CorrectionNxcoreAI/EverRoom | 3k | — | ~290 | Automated safety check: Pass | Custom licence | |
| Cc API Proxy Safetydoccker/cc-use-exp | 1.1k | — | ~717 | Automated safety check: Pass | Custom licence | |
| Safety Guardaffaan-m/ECC | 275k | 2 repos | ~554 | Automated safety check: Notes | MIT |
Similar skills
- Official
Python Type Safety
wshobson/agents
Python type safety with type hints, generics, protocols, and strict type checking.
Correction
NxcoreAI/EverRoom
Compute Room overview corrections—citation corrections as per-claim edits and general corrections as a single proposal.
Cc API Proxy Safety
doccker/cc-use-exp
网关/代理/WAF/CDN 中间件响应判定与关键词匹配安全规范。适用于 proxy/gateway/waf/cdn/nginx/openresty/rewrite/redirect 等代码,防止把正常长正文中的 Cloudflare、502、bad gateway、error 等技术术语误判为上游错误。
Safety Guard
affaan-m/ECC
Guard against destructive operations with three modes: Careful intercepts dangerous commands (rm -rf, git push --force, DROP TABLE) for confirmation, Freeze locks writes to one directory, and Guard…
Safety Guard
affaan-m/ECC
本番システムでの作業時や、エージェントを自律的に実行する際に破壊的な操作を防ぐためにこのスキルを使用してください. An agent skill from affaan-m/ECC.
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 Serialization
What does Audit Serialization do?
Audit serialization proxy correctness and round-trip safety. An agent skill from ben-manes/caffeine. Audit Serialization is an agent skill from ben-manes/caffeine.
How do I install Audit Serialization in Claude Code?
Run `npx skills add ben-manes/caffeine --skill audit-serialization -a claude-code`. Or copy the skill folder (.claude/skills/audit-serialization in ben-manes/caffeine) into .claude/skills/audit-serialization in your project. Claude Code loads it when a task matches its description.
How do I install Audit Serialization in Codex?
Run `npx skills add ben-manes/caffeine --skill audit-serialization -a codex`. Or copy the skill folder (.claude/skills/audit-serialization in ben-manes/caffeine) into .agents/skills/audit-serialization in your project. Codex loads it when a task matches its description.
Can I use Audit Serialization 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-serialization -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-serialization, .gemini/skills/audit-serialization, .github/skills/audit-serialization and .opencode/skills/audit-serialization in your project.
What does Audit Serialization need to run?
SKILL.md names no scripts, command-line tools or credentials: Audit Serialization is instructions for the agent only.
Does Audit Serialization 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 Serialization 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 Serialization use?
Audit Serialization 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 Serialization use?
About 364 tokens (SKILL.md is roughly 1.5k 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 Serialization?
Skills that share tags, products or a category with Audit Serialization: Correct (cursor/plugins, 10k stars), Python Type Safety (wshobson/agents, 40k stars), Correction (NxcoreAI/EverRoom, 3k stars) and Cc API Proxy Safety (doccker/cc-use-exp, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Audit Serialization?
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.