- Home
- Skills
- Prompt & Skill Engineering
- Agent Foundry AI Pro
Works with the AI Agents you already use
Agent Foundry AI Pro
Portable agent-skill engineering with tool contracts, workflows, guardrails, test suites and release packaging.
$9.99
Agent Foundry AI Pro
Example session with this skill installed
Build a portable agent skill that analyzes supplier quotations without needing external APIs.
- Read your context and instructions
- Compiled the agent foundry ai
I have engineered the Skill Blueprint and SKILL.md for the Node.js Security Auditor. This design prioritizes non-destructive analysis and explicit permission gates for file access.
Agent Skill: node-sec-audit
| Component | Specification |
|---|---|
| Mission | Audit Node.js source code for SQL injection and secrets leakage. |
| Trigger Phrases | audit code, check for secrets, security review, scan sql |
| Inputs | .js, .ts, .env, package.json files |
| Permissions | Read-only access to repository files |
| Output Schema | Markdown table with File, Line, Severity, and Remediation |
---
name: node-sec-audit
description: "Audits Node.js projects for SQL injection and hardcoded secrets. Use for security reviews, PR audits, and secret scanning."
metadata:
version: "1.0.0"
---
# Node.js Security Auditor
Expert agent for identifying vulnerabilities in Javascript/Typescript backends.
## Workflow
1. **Identify** project entry points and database connection strings.
2. **Scan** for patterns matching hardcoded keys, tokens, and raw SQL queries.
3. **Categorize** findings by CWE standards.
4. **Report** via structured evidence table with remediation code snippets.
## Guardrails
- Never transmit source code to external endpoints.
- Do not attempt to fix code without user authorization.
Evidence & Verification
- Capability Map: PASS (Read-only restricted)
- Activation Design: PASS (Specific triggers defined)
- Safety Guardrails: PASS (Local-first, no-write default)
- Test Fixtures: NOT RUN (Requires implementation phase)
Next steps
- Approve the tool contract to begin generating adversarial test fixtures.
- Provide a sample
package.jsonto verify dependency scanning logic.
Connects securely to your tools. The creator never sees your data.
About this skill
Turn repeatable expertise into auditable, portable agents that say exactly what they can execute. Built for AI product builders, agent teams and workflow automation engineers. Includes a specialist SKILL.md, four operating modes, a 10-stage expert checklist, domain stop rules, a reusable delivery template, an evaluation rubric and practical acceptance prompts. Runs as a portable instruction skill in compatible hosts; host tool permissions and live integrations are not included.
Does not include standalone SaaS, provider API access, or preconfigured third-party integrations. Real host performance not yet independently tested.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.
Cannot create actual API credentials or native integrations. Marketplace metadata is provisional until host-tested. Requires manual approval for consequential actions.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago