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/vasilyu1983/AI-Agents-publicnpx agentmods add skills/vasilyu1983/ai-agents-public/agents-mcpWrote 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/vasilyu1983/ai-agents-public/agents-mcp)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/agents-mcp"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/agents-mcp/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/vasilyu1983/ai-agents-public/agents-mcp"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/agents-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 78 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- high Agent Snooping · line 95 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 98 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 105 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Rogue Agent · line 31 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 63 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 177 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 185 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 191 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00039 | $0.06734 |
| Opus 5 | $0.00019 | $0.03367 |
| Sonnet 5 | $0.00008 | $0.01347 |
| Haiku 4.5 | $0.00004 | $0.00673 |
Grade B, and why
agents-mcp scanned grade B 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Editing `~/.codex/config.toml` directly is still the only path for fields the CLI doesn't expose yet — modular tool gating (`enabled_tools`/`disabled_tools`, `default_tools_approval_mode`), static `http_headers`, and OAu How it starts
The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP (Model Context Protocol)
Use this skill to decide whether MCP is the right abstraction, configure existing servers in Claude Code or Codex, or build a narrow custom server when repeated agent workflows justify it.
Protocol baseline: 2026-07-28 is the current spec — it shipped on 2026-07-28 (https://modelcontextprotocol.io/specification/2026-07-28/changelog), superseding 2025-11-25. It is a fundamental redesign, not an increment:
- Stateless protocol. The
initialize/notifications/initializedhandshake and theMcp-Session-Idheader are removed (SEP-2567, SEP-2575). Every request carries its protocol version and client capabilities in_meta; a mandatoryserver/discoverRPC advertises supported versions and identity. Servers needing cross-call state mint explicit handles passed as ordinary tool arguments. - Roots, Sampling, and Logging are deprecated (SEP-2577) — still functional, but new implementations should not adopt them. Migrate to tool-parameter directories / resource URIs, direct LLM provider API calls, and stderr or OpenTelemetry respectively.
- Server-initiated requests are gone.
roots/list,sampling/createMessage, andelicitation/createare replaced by the Multi Round-Trip Requests (MRTR) pattern: the server returnsresultType: "input_required"withinputRequests, and the client retries the original request carryinginputResponses. - Transport changes. The HTTP GET endpoint and
resources/subscribe/unsubscribecollapse into a singlesubscriptions/listenstream; SSE resumability (Last-Event-ID) is removed, so a broken stream means re-issuing the request with a new ID.pingandlogging/setLevelare removed. HTTP+SSE transport is now formally Deprecated — migrate to Streamable HTTP.
The deprecation clock is the planning fact that matters. The spec adopted a formal feature lifecycle (Active / Deprecated / Removed) with a minimum twelve-month deprecation window (SEP-2596) and a published deprecated features registry. Anything you build on Roots, Sampling, or Logging today has a bounded, published lifetime — treat those as migration debt from the start rather than as supported surface. Verify the registry for current state before relying on a deprecated feature; the window is a floor, not a promise of a specific removal date.
TypeScript SDK v2 targets this spec; v1.x remains a supported production lane for a transition period. Confirm current SDK stability against the SDK repo before choosing a lane — that status moves independently of the spec.
Governance (factor into vendor-trust judgment, not just the tech): Anthropic donated MCP to the Agentic AI Foundation (AAIF), a directed fund under the Linux Foundation, effective 2025-12-09 (blog.modelcontextprotocol.io/posts/2025-12-09-mcp-joins-agentic-ai-foundation; AAIF founding members include AWS, Anthropic, Block, Bloomberg, Cloudflare, Google, Microsoft, and OpenAI). The existing maintainers keep full technical authority over the spec via the SEP process — the foundation explicitly "will not dictate the technical direction of MCP" — so day-to-day spec/SDK guidance in this skill is unaffected. What changes for your judgment: MCP is no longer a single-vendor bet, which lowers long-term protocol-abandonment risk and is a legitimate factor when a customer or security review asks "who owns this protocol" — cite the foundation, not Anthropic, when that question comes up.
What ships with it
18 files 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.
- agents/openai.yaml 329 B
- assets/api/template-mcp-api.md 15 KB
- assets/database/template-mcp-database.md 15 KB
- assets/deployment/template-mcp-docker.md 12 KB
- assets/filesystem/template-mcp-filesystem.md 17 KB
- data/sources.json 15 KB
- data/versions.json 2.3 KB
- learnings.consolidated.md 586 B
- learnings.md 2.9 KB
- references/mcp-custom.md 15 KB
- references/mcp-ecosystem-patterns.md 3.2 KB
- references/mcp-evaluation.md 4.3 KB
- references/mcp-for-dwh.md 26 KB
- references/mcp-patterns.md 21 KB
- references/mcp-security.md 18 KB
- references/mcp-servers.md 12 KB
- references/transport-auth-matrix.md 5.7 KB
- scripts/mcp_health_check.sh 7.0 KB runs code
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.
- 7d ago Changed · +2 lines 7e52d1baa1ce
- 11d ago First seen · 398 lines · 39 tokens per session scan B 7cdf6a224a5c
agents-mcp is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 9d ago), licensed MIT. It adds 39 tokens to every session and 6,734 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
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.
projection-patterns
Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.
microservices-patterns
Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".