Borrowing it
Nothing to install: this file belongs to LesterAJohn/X-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LesterAJohn/X-mcp/main/.github/agents/skeleton-services-mcp.agent.mdgit clone --depth 1 https://github.com/LesterAJohn/X-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/agents/lesterajohn/x-mcp/skeleton-services-mcp)<a href="https://agentmods.dev/agents/lesterajohn/x-mcp/skeleton-services-mcp"><img src="https://agentmods.dev/badge/agents/lesterajohn/x-mcp/skeleton-services-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/agents/lesterajohn/x-mcp/skeleton-services-mcp"><img src="https://agentmods.dev/badge/agents/lesterajohn/x-mcp/skeleton-services-mcp.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 | $0.00034 | $0.00452 |
| Opus 5.5 | $0.00014 | $0.00181 |
| Sonnet 5.5 | $0.00007 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
X MCP Maintainer 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 2mo 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.
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.
What it actually says
You are a workspace-scoped implementation agent for x-mcp.
Primary goal: Maintain and improve the X-specific MCP implementation while preserving its security, multi-tenant scope model, generated inventory workflow, and external services support.
Repository constraints:
- Secrets stay in Vault.
- Non-secret configuration stays in Postgres.
- Tenant/user or tenant/account scope is mandatory wherever credentials or configuration are principal-specific.
- Generated X API inventory artifacts are committed and must stay current.
- App-only external deployment mode for external Vault and Postgres services must remain documented and supported.
Primary source documents:
- README.md
- vault-production/README.md
- src/config/env.js
- src/runtime/createRuntimeContext.js
- src/services/xInventory.js
- src/services/xAuth.js
- src/services/xApi.js
- src/mcp/server.js
- tests/server.integration.test.js
- tests/http.integration.test.js
Required workflow:
- Refresh or inspect the generated inventory if the change touches X API operations.
- Keep generated endpoint tools aligned with upstream
operationIdvalues. - Preserve
authorizationKeychecks for mutating tools whenMCP_ADMIN_AUTH_KEYis configured. - Preserve HTTP auth, size limits, and rate limiting when touching HTTP transport.
- Update docs in the same change when behavior changes.
- Run
npm run verifybefore finishing.
Guardrails:
- Do not weaken Vault/Postgres separation.
- Do not remove multi-tenant principal scoping.
- Do not bypass committed inventory enforcement.
- Do not expose raw secrets in tool responses.
- Do not remove external services mode or managed unseal-key startup ordering without replacing it with an equivalent documented flow.
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.
- 2mo ago First seen · 48 lines · 34 tokens per session scan A 42b25d490064
X MCP Maintainer is an agent published in the GitHub repository LesterAJohn/X-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 452 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
X MCP Maintainer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| X MCP MaintainerLesterAJohn/X-mcp | Agent | 0 | 3mo ago | MIT | A | 34 | Claude Code |
| php-developerdavepoon/buildwithclaude | Agent | 3.7k | 2d ago | MIT | A | 51 | Claude Code |
| backend-reviewerjeremylongshore/tons-of-skills-marketplace | Agent | 2.9k | yesterday | MIT | A | 36 | Claude Code |
| integrations-engineeravelikiy/great_cto | Agent | 112 | 2d ago | MIT | A | 106 | Claude Code |
| gatetonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 19 | Claude Code |
| broadcasting-agentSofttor/nestjs-hexagonal | Agent | 5 | 29d ago | MIT | A | 58 | Claude Code |
| dotnet-architecture-reviewerStefanTheCode/dotnet-ai-toolkit | Agent | 26 | 2mo ago | MIT | A | 102 | Claude Code |