compuute-scan

compuute-scan is a skill for Claude Code, Codex from Compuute/compuute-scan-api. It costs 122 tokens per session (1,018 once invoked), scanned A, original, MIT.

A security-checking skill for public GitHub repositories that provide MCP servers, which let AI agents use external tools. It scans the code for suspicious patterns and reports finding counts, a score, severe findings, and a warning that the results need human review.

In plain words
What is it for?
Use it to review public MCP-server repositories before installing, connecting to, recommending, or documenting them.
Why use it?
It provides an initial supply-chain check before connecting an unfamiliar MCP server to an agent. The scan flags patterns to investigate, but does not prove that a vulnerability can be exploited.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

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 skills/compuute/compuute-scan-api/compuute-scan
Any agent
npx skills add Compuute/compuute-scan-api --skill compuute-scan
Clone the repo
git clone --depth 1 https://github.com/Compuute/compuute-scan-api

Made for: Claude Code, Codex.

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 compuute-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/compuute/compuute-scan-api/compuute-scan.svg)](https://agentmods.dev/skills/compuute/compuute-scan-api/compuute-scan)
Your own site
<a href="https://agentmods.dev/skills/compuute/compuute-scan-api/compuute-scan"><img src="https://agentmods.dev/badge/skills/compuute/compuute-scan-api/compuute-scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,018 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00122 $0.01018
Opus 5 $0.00061 $0.00509
Sonnet 5 $0.00024 $0.00204
Haiku 4.5 $0.00012 $0.00102

Measured 5d ago against content hash 8032aee15c61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

compuute-scan 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scan.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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

The script wraps `curl` and pretty-prints the JSON response. It returns:
skills/compuute-scan/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

compuute-scan — MCP server security scanner

This skill calls the hosted compuute-scan API to statically analyze a public GitHub MCP-server repository against 38 L1 rules across TypeScript/JavaScript, Python, Go, Rust, C#, Java, and Kotlin.

When to use

  • Before installing or connecting an agent to an MCP server you do not own
  • Before recommending an MCP server to a user
  • As part of supply-chain due diligence on third-party agent tooling
  • For procurement or compliance evidence on MCP code under review

When NOT to use

  • For private repositories — the hosted API only accepts public GitHub URLs
  • As a confirmed-vulnerability list — the scanner is a pattern-breadth detector, not an exploitability oracle; raw output has ~90% false-positive rate before manual triage
  • For non-MCP code — rules are tuned for MCP server patterns; for general code use a generic SAST tool

How to invoke

The skill calls a single HTTP endpoint. No API key needed for the free tier.

bash scan.sh https://github.com/<org>/<repo>

The script wraps curl and pretty-prints the JSON response. It returns:

  • summary — counts of critical / high / medium / low findings + files scanned
  • score — 0-100 (higher = safer)
  • recommendation — short string verdict ("AVOID", "REVIEW", "OK")
  • top_findings — up to 10 most severe with file + line + rule ID
  • performance — clone seconds + scan seconds
  • _disclaimer — explicit pattern-match-not-exploitability framing

Honest framing

compuute-scan is open-source MIT (Apache-compatible) and run by Compuute AB (Stockholm). Historical false-positive rate is ~90% on raw output, anchored against the modelcontextprotocol/servers reference repo (138 raw → 13 confirmed after triage). Per-rule FP rates are published at https://github.com/Compuute/compuute-scan-api/blob/main/docs/FP-RATES.md.

Treat the output as a triage queue: high-severity findings are signals worth reviewing, not confirmed vulnerabilities. The _disclaimer field in every response repeats this.

Read the full file on GitHub · 86 lines

Files

What ships with it

1 file 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. 5d ago First seen · 86 lines · 122 tokens per session scan A 8032aee15c61

Subscribe to this mod's changes

compuute-scan is a skill published in the GitHub repository Compuute/compuute-scan-api (0 stars, last pushed 11d ago), licensed MIT. It adds 122 tokens to every session and 1,018 once invoked, about $0.0006 per session on Opus 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.

Related

Other skills, from other repositories

clinical-trial-protocol-skill

Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for…

Agent-Threat-Rule/agent-threat-rules · 70 tokens

claude-d3js-skill

This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.

Agent-Threat-Rule/agent-threat-rules · 25 tokens

adr-skill

Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses…

Agent-Threat-Rule/agent-threat-rules · 89 tokens

terraform-skill

Terraform infrastructure as code best practices.

Agent-Threat-Rule/agent-threat-rules · 10 tokens

create-auth-skill

Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.

Agent-Threat-Rule/agent-threat-rules · 66 tokens

prior-auth-review-skill

Automate payer review of prior authorization (PA) requests. This skill should be used when users say "Review this PA request", "Process prior authorization for [procedure]", "Assess medical necessity", "Generate PA decision", or when processing clinical documentation for coverage policy validation and authorization…

Agent-Threat-Rule/agent-threat-rules · 63 tokens