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.
npx agentmods add skills/technicalpickles/pickled-claude-plugins/working-with-mcpnpx skills add technicalpickles/pickled-claude-plugins --skill working-with-mcpgit clone --depth 1 https://github.com/technicalpickles/pickled-claude-pluginsWrote 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/technicalpickles/pickled-claude-plugins/working-with-mcp)<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/working-with-mcp"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/working-with-mcp.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.02812 |
| Opus 5 | $0.00043 | $0.01406 |
| Sonnet 5 | $0.00017 | $0.00562 |
| Haiku 4.5 | $0.00009 | $0.00281 |
Grade D, and why
working-with-mcp scanned grade D with 3 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 6d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "http://127.0.0.1:8080/api/v1/servers?apikey=YOUR_KEY" | python3 -m json.tool Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
grep '"api_key"' ~/.mcpproxy/mcp_config.json Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **HTTP API** (`curl http://localhost:8080/...`) - For debugging MCPProxy itself How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with MCPProxy and MCP Tools
Overview
MCPProxy can be accessed two ways:
- MCP Tools (
mcp__MCPProxy__*) - When MCPProxy is configured as an MCP server in Claude Code - HTTP API (
curl http://localhost:8080/...) - For debugging MCPProxy itself
This skill is for #1. For debugging MCPProxy itself, use HTTP API approach sparingly.
FIRST: Detect MCPProxy Connection
When user mentions MCPProxy or MCP tools:
- "check buildkite mcp"
- "use slack mcp tools"
- Any MCPProxy tool request
YOU MUST IMMEDIATELY:
- Look at your available tools (passive observation - don't run commands)
- Scan for tools starting with
mcp__MCPProxy__
Examples of what you're looking for:
mcp__MCPProxy__retrieve_tools
mcp__MCPProxy__call_tool
mcp__MCPProxy__upstream_servers
Decision:
- ✅ See
mcp__MCPProxy__*tools? → MCPProxy is connected, use them - ❌ Don't see
mcp__MCPProxy__*tools? → MCPProxy MCP server not connected
If tools are missing, IMMEDIATELY tell user:
"MCPProxy MCP tools aren't available in this session. The MCPProxy MCP server isn't connected.
Try the
/mcpcommand and select MCPProxy to reconnect. Once reconnected, you'll have access to themcp__MCPProxy__*tools."
DO NOT:
- Try bash commands like
claude mcp listormcpproxy list-tools - Try HTTP API with curl
- Make multiple attempts with different approaches
- Try to work around the issue
Missing mcp__MCPProxy__* tools = MCPProxy MCP server not connected = Suggest /mcp reconnect. That's it.
Core Decision Tree (Passive Observation)
This is passive observation - look at tools you already have, don't run commands.
Look at your available tools (the tool list in this session)
↓
Do you see ANY tools starting with mcp__MCPProxy__*?
│
├─ YES → MCPProxy is connected
│ ├─ Discover: mcp__MCPProxy__retrieve_tools
│ └─ Call: mcp__MCPProxy__call_tool
│
└─ NO → MCPProxy MCP server not connected
└─ Tell user: "Try /mcp command to reconnect"
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.
- 6d ago First seen · 325 lines · 86 tokens per session scan D 309379edf596
working-with-mcp is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (10 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 2,812 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads mcp configuration, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
project-memory
Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.
project-retrospective
Generate a LESSONS.md from a finished project: what worked, what didn't, what to reuse, what to retire — formatted for next-project carry-over.
template-selector
Recommend the right skill bundle, agent, and workflow sequence for a new project — so media professionals can start producing instead of browsing a 394-skill library.
absolute-simplify
Use when the user wants to simplify, clean up, refactor, tidy, or refine code — their staged/unstaged git changes or a target file/path. Reduces complexity, flattens nesting, removes redundancy and dead code, scores each change by value (holding low-value churn), then runs tests to prove nothing broke. Invoke on…
absolute-ui
Build polished, intentional UIs with concrete CSS/Tailwind values — typography, color, layout, spacing, dark mode, accessibility, animations, components. Encodes specific, opinionated rules with exact values, not vague advice. Covers buttons, cards, forms, tables, navigation, dashboards, landing pages, onboarding, and…
absolute-work
End-to-end, phase-gated SDLC for AI coding agents: relentless design interview → reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge. Handles features, bugs, refactors, greenfield projects, planning breakdowns, and migrations. Triggers on "absolute work", "build this…