# Skillhawk (npm · skillhawk)

Find coding agents that run without you and which account each bills; grade and scan SKILL.md files.

- Trust score: 71/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `skillhawk`: 71/100 (this document), [markdown](https://verifymcp.io/servers/agentwik-labs-skillhawk/skillhawk.md), [page](https://verifymcp.io/servers/agentwik-labs-skillhawk/skillhawk)

## Channel facts

- Registry: `npm`
- Package: `skillhawk`
- Version: `0.5.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 674 tokens (~112/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Skillhawk MCP server?

Skillhawk runs locally as an npm package, launched with npx -y skillhawk mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add agentwik-labs-skillhawk -- npx -y skillhawk mcp
```

### Cursor

```json
{
  "mcpServers": {
    "agentwik-labs-skillhawk": {
      "command": "npx",
      "args": [
        "-y",
        "skillhawk",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "agentwik-labs-skillhawk": {
      "command": "npx",
      "args": [
        "-y",
        "skillhawk",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add agentwik-labs-skillhawk -- npx -y skillhawk mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agentwik-labs-skillhawk": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "skillhawk",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add agentwik-labs-skillhawk --command npx --arg -y --arg skillhawk --arg mcp
```

### Hermes

```yaml
mcp_servers:
  agentwik-labs-skillhawk:
    command: "npx"
    args: ["-y", "skillhawk", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "agentwik-labs-skillhawk": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "skillhawk",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add agentwik-labs-skillhawk -t stdio -c npx -a -y skillhawk mcp
```

### Other

```json
{
  "mcpServers": {
    "agentwik-labs-skillhawk": {
      "command": "npx",
      "args": [
        "-y",
        "skillhawk",
        "mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 70, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-18 (score 55, +1)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 0.4.0 → 0.5.1

### 2026-11-17 (score 54)

First indexed and scored.

## MCP tools (6)

### `map_query` (~87 tokens)

Query the repo map

Find the files and symbols (with line numbers) that match a question, using the local skillhawk map (built by `skillhawk map`). Call this before opening files; then read only the lines it points to.

Input parameters:

- `limit` (number): Max hits (default 8)
- `question` (string, required): Keywords or a short question, e.g. "where is the security scan"

### `skill_section` (~70 tokens)

Read one section of a skill

Return one heading-section of a skill's SKILL.md instead of the whole file. Omit heading to get the outline (headings with line numbers) first.

Input parameters:

- `heading` (string): Heading text (exact or partial); omit for the outline
- `skill` (string, required): Skill id or name

### `review_skill` (~92 tokens)

Review skills (grade A-F)

Grade every SKILL.md under a folder A-F with line-level findings and fixes (broken frontmatter, vague triggers, broken links, risky scripts), and check several skills together for duplicates, overlapping triggers and contradictions. Read-only. Use before installing or publishing a skill.

Input parameters:

- `path` (string): A skill folder or a folder holding several. Relative paths resolve from the folder the server was started in. Default "."

### `secure_scan` (~92 tokens)

Security scan for skills and agent config

Scan a folder for risky agent setup: secrets and pipe-to-shell in skills, unpinned or remote-package MCP servers in .mcp.json, broad permissions in .claude/settings.json, risky dependencies in skill scripts. Returns findings by severity with a fix for each. Read-only.

Input parameters:

- `path` (string): The folder to scan. Relative paths resolve from the folder the server was started in. Default "."

### `compile_skill` (~126 tokens)

Compile a skill for other agents

Convert one Claude-style skill folder into the format other agents read (claude, codex, cursor, copilot, gemini) and check the result: content kept, frontmatter valid, size limits. Writes files under the output folder only.

Input parameters:

- `out` (string): Output folder inside the working folder. Default ".skillyard/compiled".
- `path` (string, required): The skill folder (holding SKILL.md).
- `targets` (string): Comma-separated: claude, codex, cursor, copilot, gemini, or "all". Default "all".

### `check_agents` (~143 tokens)

Find agents nobody is watching

List coding agents that run without a human on this machine: agent processes (Claude Code, Codex, Gemini, Cursor, Aider...), sessions still working with no human message for hours, scheduled agents (cron, launchd/systemd, GitHub Actions schedules) with the account each one bills (subscription or API key), API keys exported by shell start-up files, and dev servers left running. Prints variable names, never values. Read-only: it never stops anything.

Input parameters:

- `idle_hours` (number): Flag sessions with no human message for this long. Default 2.
- `running_hours` (number): Flag agent processes running longer than this. Default 12.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/agentwik-labs-skillhawk/skillhawk#diagnostics

## Score history

- 2026-11-21: 71
- 2026-11-20: 71
- 2026-11-19: 70
- 2026-11-18: 55
- 2026-11-17: 54

## Common questions

### What is the Skillhawk MCP server?

Skillhawk is an MCP server listed in the public MCP registry as io.github.agentwik-labs/skillhawk. Find coding agents that run without you and which account each bills; grade and scan SKILL.md files. This page covers its npm package (skillhawk).

### Is the Skillhawk MCP server safe to use?

Skillhawk scores 71 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Skillhawk MCP server expose?

Skillhawk exposes 6 tools: map_query, skill_section, review_skill, secure_scan, compile_skill, check_agents. Their descriptions and schemas cost roughly 610 tokens of context every time the server is loaded.

### Is the Skillhawk MCP server still maintained?

Skillhawk is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Skillhawk MCP server under?

Skillhawk declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Skillhawk MCP server?

VerifyMCP ran 16 checks on Skillhawk, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/skillhawk
- Socket report: https://socket.dev/npm/package/skillhawk
- Repository: https://github.com/agentwik-labs/skillhawk
- Website: https://skillhawk.ai/tools/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/agentwik-labs-skillhawk/skillhawk.xml
- Changelog JSON feed: https://verifymcp.io/servers/agentwik-labs-skillhawk/skillhawk/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/agentwik-labs-skillhawk/skillhawk.json
- HTML version of this page: https://verifymcp.io/servers/agentwik-labs-skillhawk/skillhawk
