agentmods.dev

aio-patch-compile

aio-patch-compile is a skill for Claude Code from aiocean/claude-plugins. It costs 107 tokens per session (645 once invoked), scanned A, original, MIT.

A build procedure for applying patches to a Claude command-line program and compiling a patched binary, an executable file, for a selected computer platform.

In plain words
What is it for?
It is for applying tools/pipeline/patches.json, running the Bun compiler, and optionally building for the current architecture or several named platforms.
Why use it?
It shortens the repeatable process of turning patch definitions into a runnable Claude binary.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the aio-claude-toolkit plugin — 9 skills shipped together

not rated 4repo 1mo ago A scan 107 tokens original MIT

Good fit It is for applying tools/pipeline/patches.json, running the Bun compiler, and optionally building for the current architecture or several named platforms.

Compare 6 skills from other repositories ↓
View source ↗ aiocean/claude-plugins
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add aiocean/claude-plugins
Claude Code
/plugin install aio-claude-toolkit

Made for: Claude Code.

Or install aio-claude-toolkit, the plugin that ships this one along with the rest of its 9 skills.

Wrote 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.

agentmods badge for aio-patch-compile

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-patch-compile/github.svg)](https://agentmods.dev/skills/aiocean/claude-plugins/aio-patch-compile)
Your own site
<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-patch-compile"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-patch-compile/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.

agentmods 80×15 button for aio-patch-compile

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-patch-compile"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-patch-compile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 645 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00107 $0.00645
Opus 5.5 $0.00043 $0.00258
Sonnet 5.5 $0.00021 $0.00129
Haiku 4.5 $0.00011 $0.00064

Measured 1mo ago against content hash d0469f2480e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aio-patch-compile 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/compile.sh, tests/test-multi-arch.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/aio-claude-toolkit/skills/aio-patch-compile/SKILL.md · 51 lines

What it actually says

aio-patch-compile — apply patches + bun build

Goal

Produce one or more patched claude binaries at dist/<arch>/claude. Inner loop after editing tools/pipeline/patches.json or any tools/pipeline/sources/*.js file.

Usage

/aio-claude-toolkit:aio-patch-compile                                   # current host arch only (default)
/aio-claude-toolkit:aio-patch-compile --target=all                       # all 4 platforms
/aio-claude-toolkit:aio-patch-compile --target=darwin-arm64,linux-amd64  # csv list
STRICT=0 /aio-claude-toolkit:aio-patch-compile                           # ALLOW missing patches (NOT recommended)

Behavior

For each target arch in the list:

  1. If dist/<arch>/cli.js does NOT exist → transitively run ARCH=<arch> ./tools/extract.sh first
  2. Run ARCH=<arch> ./tools/build.sh which: inlines sources/*.js, applies patches.json (strict by default), bun-compiles → dist/<arch>/claude

Requires

  • Walk-up must find a scaffolded project
  • bun (>= 1.3 for stable cross-compile)
  • python3 (for patch + inline scripts)
  • tools/pipeline/patches.json populated (NOT empty) — compile fails fast on empty patches

Drift recovery

If compile reports MISSING patches (anchors not found in cli.js), Claude version likely shifted:

  • Read .aio-patch-setup to see the tested-against Claude version
  • Use /aio-claude-toolkit:aio-patch-anchor find <fragment> to locate new anchor
  • Update tools/pipeline/patches.json old field with new anchor text
  • Re-run compile

See docs/repatching-playbook.md (step-by-step re-anchoring recipe) and docs/patches.md (anchor selection strategy).

Implementation

Invokes ${CLAUDE_PLUGIN_ROOT}/skills/aio-patch-compile/scripts/compile.sh "$@".

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 1mo ago First seen · 51 lines · 107 tokens per session scan A d0469f2480e3

Subscribe to this mod's changes

aio-patch-compile is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 645 once invoked, about $0.0004 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 2026-08-31.

Claude CodeDevOps and cloudai-assistantai-codinganthropicclaudecli-tools
Related

Other skills, from other repositories

eval-hooks

Audit Claude Code and Codex hooks for validity, safety, and correctness across settings.json, hooks.json, config.toml, plugin, and skill or agent frontmatter hooks. Resolves each command, checks event names, handler types, matchers, exit-code and JSON decision strategy, and timeouts against each host's documented…

FlorianBruniaux/claude-code-ultimate-guide · 115 tokens

eval-skills

Audit a project or library of skills for metadata, trigger boundaries, workflow completion criteria, local resource closure, instruction economy, tool scope, effort, and routing evidence. Use before shipping skills, after importing a skill collection, or when a skill triggers too often or not at all.

FlorianBruniaux/claude-code-ultimate-guide · 60 tokens

source-command-audit-whitepapers

Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards.

FlorianBruniaux/claude-code-ultimate-guide · 26 tokens

audit-agents-skills

Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.

FlorianBruniaux/claude-code-ultimate-guide · 41 tokens

design-patterns

Detect, suggest, and evaluate GoF design patterns in TypeScript/JavaScript codebases. Use when refactoring code, applying singleton/factory/observer/strategy patterns, reviewing pattern quality, or finding stack-native alternatives for React, Angular, NestJS, and Vue.

FlorianBruniaux/claude-code-ultimate-guide · 59 tokens

eval-agents

Audit custom subagent definitions for Claude Code (.claude/agents/.md) and Codex (.codex/agents/.toml): loadability against the native schema, description overlap, model tier, tool scope, and headless-safe instructions. Use when onboarding to a project with agents, after adding or importing agents, or when the parent…

FlorianBruniaux/claude-code-ultimate-guide · 80 tokens