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.
/plugin marketplace add aiocean/claude-plugins/plugin install aio-claude-toolkitWrote 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/aiocean/claude-plugins/aio-patch-control)<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-patch-control"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-patch-control/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/aiocean/claude-plugins/aio-patch-control"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-patch-control.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 | $0.00098 | $0.00460 |
| Opus 5.5 | $0.00039 | $0.00184 |
| Sonnet 5.5 | $0.00020 | $0.00092 |
| Haiku 4.5 | $0.00010 | $0.00046 |
Grade A, and why
aio-patch-control scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `control/simple-client.sh`, `raw-client.sh` — minimal curl-based clients What it actually says
aio-patch-control — HTTP control-channel reference + docs
Goal
Drop a working sample gateway into <project>/control/ so you can drive your patched claude binary over HTTP/SSE if your patches.json injects an HTTP server (the dirty-claude pattern). Also expose the protocol docs.
Usage
/aio-claude-toolkit:aio-patch-control scaffold # copy sample scripts into ./control/
/aio-claude-toolkit:aio-patch-control docs # print docs/control-channel.md
FORCE=1 /aio-claude-toolkit:aio-patch-control scaffold # overwrite existing ./control/
What scaffold ships
control/simple-client.sh,raw-client.sh— minimal curl-based clientscontrol/stream-client.sh,stream-text.sh,stream-ambient.sh— SSE streaming variantscontrol/interactive-client.sh— line-oriented drivercontrol/client.ts— bun TUI (richer UX)control/README.md— quick reference
Requires
- Scaffolded project (walk-up sentinel) — your patches.json must inject an HTTP control-channel for these clients to actually talk to the binary
- For bun TUI:
buninstalled
Implementation
Invokes ${CLAUDE_PLUGIN_ROOT}/skills/aio-patch-control/scripts/control.sh "$@".
What ships with it
10 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.
- scripts/control.sh 1.6 KB runs code
- templates/control/client.ts 14 KB runs code
- templates/control/interactive-client.sh 629 B runs code
- templates/control/raw-client.sh 1.7 KB runs code
- templates/control/README.md 11 KB
- templates/control/simple-client.sh 838 B runs code
- templates/control/stream-ambient.sh 2.8 KB runs code
- templates/control/stream-client.sh 1.7 KB runs code
- templates/control/stream-text.sh 5.1 KB runs code
- tests/test-scaffold.sh 1001 B runs code
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 First seen · 40 lines · 98 tokens per session scan A 956faec39ef5
aio-patch-control is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 460 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
vellum-oauth-integrations
Act on behalf of your user in any third-party software that supports OAuth 2.0.
clerk-authentication
Guidelines for implementing Clerk authentication in Next.js applications with middleware, hooks, and security best practices.
grpc-development
Best practices for building high-performance services with gRPC and Protocol Buffers. Use when designing RPC services, defining protobuf schemas, implementing streaming APIs, setting up gRPC interceptors, or building cross-language service communication.
cheerio-parsing
Expert guidance for HTML/XML parsing using Cheerio in Node.js with best practices for DOM traversal, data extraction, and efficient scraping pipelines.
express-typescript
Guidelines for building robust APIs with Express.js and TypeScript, covering middleware patterns, routing, and security best practices.
gcp-development
Google Cloud Platform (GCP) development best practices for Cloud Functions, Cloud Run, Firestore, BigQuery, and Infrastructure as Code.