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 skills add agentic-community/mcp-gateway-registry --skill usage-report-v0git clone --depth 1 https://github.com/agentic-community/mcp-gateway-registryWrote 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/agentic-community/mcp-gateway-registry/usage-report-v0)<a href="https://agentmods.dev/skills/agentic-community/mcp-gateway-registry/usage-report-v0"><img src="https://agentmods.dev/badge/skills/agentic-community/mcp-gateway-registry/usage-report-v0/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/agentic-community/mcp-gateway-registry/usage-report-v0"><img src="https://agentmods.dev/badge/skills/agentic-community/mcp-gateway-registry/usage-report-v0.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 | $0.00053 | $0.10841 |
| Opus 5 | $0.00026 | $0.05421 |
| Sonnet 5 | $0.00011 | $0.02168 |
| Haiku 4.5 | $0.00005 | $0.01084 |
Grade D, and why
usage-report-v0 scanned grade D with 2 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
which pandoc >/dev/null || sudo apt-get install -y pandoc Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
1. **SSH key** at `~/.ssh/id_ed25519` with access to the bastion host How it starts
The opening of the file, as written. The whole thing — 711 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARCHIVED, DOC-ONLY REFERENCE. Do not invoke this skill for production reports. Use
/usage-reportinstead.Comparison-mode usage: This skill can be run AFTER
/usage-reporthas already populated.scratchpad/usage-reports/<DATE>/with the bastion export, analyzer JSON/CSV files, and PNG charts. In comparison mode you skip Steps 1-6 (the bastion export and analyzer runs) and jump straight to Step 7 (LLM writes the report by reading the existing files). The output is a v0-style LLM-written report alongside the new deterministic + commentary report, useful for side-by-side prose voice / structure comparison.This SKILL.md captures the report-generation approach that was on
mainat commitf1c0c14a(2026-06-07), before the deterministic-render refactor. At that point the LLM did the report writing: it ran the analyzer scripts, then wrote the entire markdown by reading their outputs and synthesizing prose. The hallucination bug class we hit (Azure 28 vs 47, etc.) was the motivation to move to the template + augment-with-commentary architecture used in the current/usage-reportskill.Kept here for:
- Side-by-side comparison runs against
/usage-reportoutput for the same date.- Comparing prose voice and section structure between the old LLM-written reports and the new deterministic+commentary reports.
- Recovering specific narrative patterns (e.g., "the longevity tier is now an aws/ecs/entra phenomenon") that were good and worth porting forward.
- Auditing what the old skill's instructions told the LLM to do, to make sure no semantic content was lost in the migration.
The .py scripts referenced below (
analyze_telemetry.py,analyze_liveness.py, the chart generators, etc.) live in.claude/skills/usage-report/. This v0 folder contains only this SKILL.md.Comparison-mode workflow (recommended):
- Run
/usage-reportfirst for date<DATE>. This produces the deterministic report and populates.scratchpad/usage-reports/<DATE>/with all data files and charts.- Then invoke this archived skill in comparison mode: skip Steps 1-6 (data is already exported), and start at Step 7 to have the LLM write a v0-style report from the existing files.
- Save the v0 output as
ai-registry-usage-report-<DATE>-v0.mdin the same dated folder, next to the deterministicai-registry-usage-report-<DATE>.md.
Usage Report Skill (archived)
Export telemetry data from the MCP Gateway Registry's DocumentDB telemetry collector and generate a usage report showing deployment patterns, version adoption, and feature usage in the wild.
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 · 711 lines · 53 tokens per session scan D 6f0a1d332a09
usage-report-v0 is a skill published in the GitHub repository agentic-community/mcp-gateway-registry (903 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 10,841 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.