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/sandraschi/plexmcp/plex-mcp-roadmapnpx skills add sandraschi/plexmcp --skill plex-mcp-roadmapgit clone --depth 1 https://github.com/sandraschi/plexmcpWrote 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/sandraschi/plexmcp/plex-mcp-roadmap)<a href="https://agentmods.dev/skills/sandraschi/plexmcp/plex-mcp-roadmap"><img src="https://agentmods.dev/badge/skills/sandraschi/plexmcp/plex-mcp-roadmap.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 | $0.00078 | $0.01207 |
| Opus 5 | $0.00039 | $0.00603 |
| Sonnet 5 | $0.00016 | $0.00241 |
| Haiku 4.5 | $0.00008 | $0.00121 |
Grade A, and why
plex-mcp-roadmap 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plex-mcp Roadmap — Orchestrator
You are implementing features for plex-mcp, a FastMCP 3.2 server
for Plex Media Server. Roadmap in docs/plans/ROADMAP.md with six
child projects in the same directory.
Activate this skill when
The user asks to build any of:
- Deep metadata enrichment (Wikipedia + TMDB + Letterboxd + IMDB + RT + Metacritic + Criterion)
- Subtitle RAG (semantic search across all subtitles, with Whisper fallback)
- Taste modelling (user preference profile from watch history)
- Mood-based nightly picker (taste-aware "what to watch tonight")
- Episode intelligence (per-episode summaries, character arcs, "recap before watching")
- Cross-library linking (director/cast/adaptation/making-of pairs)
For any of these: read docs/plans/ROADMAP.md, then the
per-project spec, then use the matching per-project skill.
Shared conventions
Layout
- Main package:
src/plex_mcp/ - Tools:
src/plex_mcp/tools/ - Services:
src/plex_mcp/services/ - RAG:
src/plex_mcp/rag/ - Webapp backend:
webapp/backend/app/ - Webapp frontend:
webapp/frontend/app/(Next.js App Router)
Ports (never change)
- Backend FastAPI + MCP HTTP: 10741
- Frontend Next.js: 10742
- Plex: 32400 (external)
- Ollama: 11434 (external)
Tool patterns
All tools use @mcp.tool() via the global plex_mcp.server.mcp
instance. New portmanteau tools: src/plex_mcp/tools/{category}/ manage_{thing}.py with Literal operation parameter.
REST pattern
Endpoints in webapp/backend/app/api/{feature}.py. Routers
registered in webapp/backend/app/main.py. Frontend catch-all
rewrite /api/:path* → :10741/api/:path* is already in place.
PlexAPI usage
All Plex interaction via plexapi (already a dep). Never make
raw HTTP calls to Plex. Use the central PlexService singleton
in src/plex_mcp/services/plex_service.py.
State DB
All user-state tables in the plex-mcp SQLite DB (not Plex's own
metadata.db — NEVER write to that). New tables: include
created_at, updated_at TIMESTAMP columns.
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.
- 3d ago First seen · 120 lines · 78 tokens per session scan A ee00856cb9cc
plex-mcp-roadmap is a skill published in the GitHub repository sandraschi/plexmcp (2 stars, last pushed 16d ago), licensed MIT. It adds 78 tokens to every session and 1,207 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
blender-expert
Expert Blender 3D modeling, animation, rendering, and pipeline automation. Use for any Blender-related task from simple primitives to complex procedural workflows.
blender-mcp
Blender 3D automation via FastMCP — modeling, animation, rendering, scene management, materials, and more.
discord-rag
Retrieval-Augmented Generation over Discord message history. Ingest channel messages into a local LanceDB vector database, then search semantically — find messages about a topic even when the exact words don't match.
debug-evals
Debug haiku.rag evaluation runs in Logfire. Use when asked to look at Logfire for an eval run, find failing or low-scoring eval cases, compare runs, check citation quality (citedmap) or judge pass rate (answerequivalent), or explain why an eval case failed. Drives the Logfire MCP against the evals service, or the…
debug-ingestion
Debug haiku.rag ingestion in Logfire. Use when asked to look at Logfire for ingestion, find failed or dead ingestion jobs, investigate retries or circuit-breaker events, trace a document through convert/chunk/embed/store, find which docling-serve instance served a request, spot slow conversions, or tell concurrent…
autonomous-modeling
Use this skill to autonomously design and model complex 3D objects in Blender. Perfect for generating chassis, robots, and environment props from natural language.