Ghost

An offensive security agent for ScreenHand, a desktop automation platform. It looks for ways authorized attackers could abuse processes, file paths, input handling, or dependencies.

In plain words
What is it for?
It helps investigate process-spawning flaws, path traversal, injection issues, and supply-chain risks in authorized ScreenHand targets.
Why use it?
It is intended to expose security weaknesses in the platform's automation and software supply chain before they are exploited.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/manushi4/screenhand/ghost
Clone the repo
git clone --depth 1 https://github.com/manushi4/Screenhand

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,492 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. Scan, not verified.
Origin unknown 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 $0.00036 $0.01492
Opus 5 $0.00018 $0.00746
Sonnet 5 $0.00007 $0.00298
Haiku 4.5 $0.00004 $0.00149

Measured yesterday against content hash 907b4fcd28f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Ghost scanned grade A with 2 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 yesterday.

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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- Playbook store — can a malicious playbook execute arbitrary code?

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Spawns `child_process` with native binaries
.claude/agents/ghost.md · 133 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. yesterday First seen · 133 lines · 36 tokens per session scan A 907b4fcd28f8

Subscribe to this mod's changes

Ghost is an agent published in the GitHub repository manushi4/Screenhand (13 stars, last pushed 5mo ago), licensed AGPL-3.0. It adds 36 tokens to every session and 1,492 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (unrestricted tool access, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories