Borrowing it
Nothing to install: this file belongs to abrahamADSK/fpt-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/abrahamADSK/fpt-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/abrahamADSK/fpt-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/instructions/abrahamadsk/fpt-mcp/claude-md)<a href="https://agentmods.dev/instructions/abrahamadsk/fpt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/abrahamadsk/fpt-mcp/claude-md/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/instructions/abrahamadsk/fpt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/abrahamadsk/fpt-mcp/claude-md.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 | $0.10154 | $0.10154 |
| Opus 5.5 | $0.04062 | $0.04062 |
| Sonnet 5.5 | $0.02031 | $0.02031 |
| Haiku 4.5 | $0.01015 | $0.01015 |
Grade C, and why
fpt-mcp CLAUDE.md scanned grade C 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 1mo 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- ALWAYS use MCP tools, NEVER tell the user "do it manually" Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
In `~/.claude/settings.json`, enable all these tools: How it starts
The opening of the file, as written. The whole thing — 651 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fpt-mcp Project Context for Claude
Reference document that persists across sessions. Update when architecture or workflows change.
1. General Architecture
fpt-mcp is an MCP server for Autodesk Flow Production Tracking (ShotGrid). Works standalone or alongside other MCP servers for cross-tool orchestration.
Claude Desktop / Claude Code / Terminal
├── maya-mcp → 3D modeling, rendering, Vision3D GPU
├── flame-mcp → compositing
└── fpt-mcp → production tracking (ShotGrid)
├── stdio → Claude Desktop / Claude Code
├── HTTP → Maya, Flame, scripts, inter-service
└── Qt console → native chat app via fpt-mcp:// protocol handler
MCP Server: fpt-mcp (18 @mcp.tool registrations — dispatcher pattern)
ShotGrid API tools (6 direct tools, unrestricted access to any entity):
sg_find— query entities with filters and fieldssg_create— create entities (project auto-linked)sg_update— update any fieldsg_schema— inspect available fieldssg_upload— upload files (thumbnail, movie, attachment)sg_download— download attachments
Bulk operations dispatcher (fpt_bulk — 1 tool, 5 actions):
fpt_bulk(action="delete")— soft-delete (retire) entitiesfpt_bulk(action="revive")— restore soft-deleted (retired) entitiesfpt_bulk(action="batch")— transactional batch operations (all-or-nothing)fpt_bulk(action="editorial")— deterministic Cut + CutItem auto-calc: pure timecode math (editorial.py::compute_editorial_cut) computes cumulativeedit_in/edit_outandcut_item_in/cut_item_out(source range) in Autodesk's importer convention (1-based, inclusive) plussg_cut_duration;compute_shot_handle_updatesputs handles on the Shot (sg_head_in/sg_tail_out), never on the CutItem. A thin creation layer (shotgrid.py::_do_sg_editorial) creates the Cut viasg_createand the CutItems (+ Shot handle updates whenhandles > 0) via onesg_batchtransactionfpt_bulk(action="link_task")— link a native tk-flame delivery (version_id+step) to its Task: the Version, its publishes and the Shot's Task-less publishes with the same version number, in onesg_batch. tk-flame leaves them Task-less because tk-core only yields a Task from a Task-typed schema folder (Chat 108). Exactly one Task must match; any record on a different Task aborts the write; idempotent
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.
- 1mo ago Changed · +68 tokens per session 2594d3374996
- 1mo ago Changed · +14 lines · +335 tokens per session 9cbe38179aa7
- 1mo ago Changed · +5 lines · +84 tokens per session a62d31f0f781
- 1mo ago Changed · +14 lines · +168 tokens per session a1997eac27da
- 2mo ago First seen · 618 lines · 9,499 tokens per session scan C 73ab8a789c6c
fpt-mcp CLAUDE.md is an instructions file published in the GitHub repository abrahamADSK/fpt-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 10,154 tokens to every session, about $0.0406 per session on Opus 5.5. A static security scan graded it C with 2 findings (subtle steering, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
fpt-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fpt-mcp CLAUDE.mdabrahamADSK/fpt-mcp | Instructions file | 2 | 1mo ago | MIT | C | 10,154 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |