Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/faberlens/hardened-skillsnpx agentmods add skills/faberlens/hardened-skills/api-client-hardenedWrote 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/faberlens/hardened-skills/api-client-hardened)<a href="https://agentmods.dev/skills/faberlens/hardened-skills/api-client-hardened"><img src="https://agentmods.dev/badge/skills/faberlens/hardened-skills/api-client-hardened/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/faberlens/hardened-skills/api-client-hardened"><img src="https://agentmods.dev/badge/skills/faberlens/hardened-skills/api-client-hardened.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 | $0.00035 | $0.05358 |
| Opus 5 | $0.00017 | $0.02679 |
| Sonnet 5 | $0.00007 | $0.01072 |
| Haiku 4.5 | $0.00003 | $0.00536 |
Grade A, and why
postman-hardened 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 10d 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.
│ ├── postman_client.py # API client with CRUD + Spec Hub operations (now uses curl) How it starts
The opening of the file, as written. The whole thing — 596 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Postman Agent Skill
Version: 1.1.0 (Phase 1 - Core API Compatibility) API Support: Postman v10+ (with v9 graceful degradation)
🚀 Quick Start
When you first use this skill, Claude will automatically:
- ✅ Validate your API key and connection
- 📁 Check your workspace configuration
- 📊 Count your collections and resources
- 💡 Suggest next steps if setup is incomplete
First time setup validation:
# Claude will run this automatically on first use
python scripts/validate_setup.py
Common first questions that work immediately:
- "How many collections do I have?" - Lists all collections in your workspace
- "Show me my workspaces" - Displays available workspaces
- "Validate my setup" - Runs comprehensive diagnostics
- "Create a new collection called 'Test API'" - Starts building immediately
🤖 Note for Claude: On first use of this skill in a conversation, ALWAYS run:
python scripts/validate_setup.py
This provides immediate diagnostics and context before proceeding with the user's request.
✅ Network Compatibility
This skill works across multiple Claude environments with proper proxy configuration.
Where This Skill Works
| Environment | Status | Notes |
|---|---|---|
| Claude Web Interface | ✅ Fully Supported | Works with configured proxy |
| Claude API (Code Execution) | ✅ Fully Supported | No network restrictions |
| Local Python Scripts | ✅ Fully Supported | Direct execution on your machine |
| Claude Desktop | ⚠️ Limited | Requires api.getpostman.com in network allowlist |
Proxy Configuration
The skill is designed to work with proxy environments:
- Keeps proxy environment variables intact for proper DNS resolution
- Handles nested HTTP responses from proxy servers
- Supports HTTP/2 responses through proxies
- Debug mode available with
POSTMAN_DEBUG=1environment variable
How to Use This Skill
Option 1: Claude Web Interface (Recommended) Use the skill directly in Claude web interface. The proxy is pre-configured and handles all network requests automatically.
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.
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.
- 10d ago First seen · 596 lines · 35 tokens per session scan A 077d62c675a0
postman-hardened is a skill published in the GitHub repository faberlens/hardened-skills (23 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 5,358 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
llm-evaluation
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
write-unit-tests
Writing unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages/tldraw. Covers Vitest patterns, TestEditor usage, and test file organization.
email-api
Manage emails via REST API - send, read, search, delete emails, manage contacts, upload files, and store data. Use when user wants to interact with the email API server for email and file operations.
smoke-test
Start the Registry Server via docker compose and run a suite of curl-based smoke tests covering system, read-only MCP API, admin API, entry lifecycle, and OAuth/auth enforcement scenarios.
bats-testing-patterns
\"Master Bash Automated Testing System (Bats) for comprehensive shell script testing. Use when writing tests for shell scripts, CI/CD pipelines, or requiring test-driven development of shell utilities.\".
mcp
This skill MUST be invoked when users want to create, build, or develop MCP (Model Context Protocol) servers. Should be used for any task involving MCP server creation, whether simple calculator tools or complex API integrations. Covers FastMCP (Python) and MCP SDK (Node/TypeScript) implementations, tool design…