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/florianbruniaux/claude-code-plugins/mcp-integration-referencenpx skills add FlorianBruniaux/claude-code-plugins --skill mcp-integration-referencegit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-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/florianbruniaux/claude-code-plugins/mcp-integration-reference)<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/mcp-integration-reference"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/mcp-integration-reference.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 | $0.00061 | $0.01037 |
| Opus 5 | $0.00030 | $0.00518 |
| Sonnet 5 | $0.00012 | $0.00207 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
mcp-integration-reference scanned grade A with 0 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 today.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Integration Reference Pattern
This is a template skill. It shows how to structure a skill that wraps an MCP server. Replace
sentrywith your MCP server name and adapt the reference file atreferences/sentry-mcp.md.
What This Pattern Solves
When a skill calls an MCP server without prior context, Claude guesses at the query syntax. This works for simple calls but breaks on anything with non-obvious behavior: pagination quirks, required parameter combinations, rate limits, or subtle format restrictions.
The fix: a references/<mcp-name>.md file that captures all the gotchas. The skill reads this file before making any MCP call. Zero guessing.
Three types of content go in the reference file:
- Parameter semantics that differ from what the tool name implies
- Known error patterns and their root causes
- Working query examples (copy-paste, no thinking required)
Step 1: Read the MCP Reference File
Before doing anything else, read the full MCP reference:
Read: references/sentry-mcp.md
This file contains query syntax, known gotchas, and working examples for the Sentry MCP. Do not skip this step.
Step 2: Gather Scope from User
Ask the user:
- Time range: Last 24h? 7 days? Custom range?
- Environments:
production,staging, or both? - Projects: All projects or specific ones? (Default: all)
If the user says "just run it with defaults", use:
- Time range: last 72 hours
- Environment:
productiononly - Projects: all
Step 3: Fetch Error Data
Using the tool knowledge from Step 1, fetch:
- Issue list: Active unresolved issues, ordered by frequency
- Event details: Full stack traces for the top 5 issues by event count
Cap results at 50 issues. If more exist, note the count and focus on the highest-frequency items.
Step 4: Group and Analyze
Group issues by root cause, not by error message. Two issues with different messages can share the same underlying cause (shared code path, same external dependency, same config).
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.
- today First seen · 139 lines · 61 tokens per session scan A 89356e3bdaa3
mcp-integration-reference is a skill published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 1,037 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
vc-autopilot
Emit and validate the provisional goal block for Autopilot Mode. Owns the 9-field format and resume detection from a pasted goal block.
vc-problem-solving
Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, scale uncertainty.
thoroughness-scoring
Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.
report
Read the delivery log and say which rules actually fire, which never have, and what to prune or fix. Use when the user asks whether ballast is doing anything, wants to clean up their rule catalog, or on a periodic review.
orchestrate
Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
squid-self-improve
Analyze developer corrections from the current coding session and persist lessons learned as rules in AGENTS.md files or memory. Use at the end of a session after the developer corrected your work, when they say "squid-self-improve", ask to capture what was learned, or ask you to reflect on mistakes and extract…