Borrowing it
Nothing to install: this file belongs to jovaneyck/fsi-mcp-server. 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/jovaneyck/fsi-mcp-server/main/.claude/commands/fsi-client.mdgit clone --depth 1 https://github.com/jovaneyck/fsi-mcp-serverWrote 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/commands/jovaneyck/fsi-mcp-server/fsi-client)<a href="https://agentmods.dev/commands/jovaneyck/fsi-mcp-server/fsi-client"><img src="https://agentmods.dev/badge/commands/jovaneyck/fsi-mcp-server/fsi-client/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/commands/jovaneyck/fsi-mcp-server/fsi-client"><img src="https://agentmods.dev/badge/commands/jovaneyck/fsi-mcp-server/fsi-client.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 | $0.00000 | $0.02490 |
| Opus 5 | $0.00000 | $0.01245 |
| Sonnet 5 | $0.00000 | $0.00498 |
| Haiku 4.5 | $0.00000 | $0.00249 |
Grade A, and why
fsi-client 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 9d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FSI Server Integration Guide for Claude Code
This guide explains how to collaborate with the FSI server through the fsi-server mcp server.
MCP-Based FSI Session Integration
Agents send over commands through MCP and can look at fsi outputs through MCP. The user can also directly input statements in the fsi.exe console. The agent can follow along with what the user enters and the results from those statements through the MCP endpoints.
Workflow for F# Code Execution
When executing F# code, follow this MCP-based workflow:
1. Add Code to Collaborative Script FIRST
CRITICAL WORKFLOW: ALWAYS add code to the .fsx file FIRST using the Edit tool, THEN send to FSI over mcp. This maintains the collaborative script as the authoritative source of truth.
NEVER develop substantial code only in FSI - the .fsx file is our collaborative workspace and must stay current.
2. Send Code to FSI via MCP
CRITICAL: All F# code sent via MCP must end with ;; to execute.
3. Read FSI Response
After file processing, check the response through MCP
4. Validate Execution
CRITICAL: After sending code to FSI, ALWAYS check the fsi output through the MCP server. If there are compilation errors, runtime errors, or any failures, ALERT the user immediately with "ALERT: We have a problem!" and describe the specific error. NEVER report work as "done" or "complete" if there are any errors in the response.
5. FSI State Management - CRITICAL
FSI maintains persistent state between executions. This creates potential inconsistencies between your .fsx file and the running FSI session.
FSI Session Restart: For major changes or when debug code pollutes the session and is causing aliasing/shadowing issues:
- Tell user: "Please restart your FSI session to clear all old function definitions"
- Then reload the complete .fsx file content over mcp
Example Execution Pattern
# 1. Add to collaborative script (WITHOUT ;; and no attribution comments)
Edit scratch.fsx to append: let result = 42 * 2
# 2. Execute in FSI via MCP (WITH ;; at the end of the content)
Content: "let result = 42 * 2;;"
# 3. Read response using MCP
# 4. Work as a silent English-to-F# interpreter - the user sees all results in their FSI session window.
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.
- 9d ago First seen · 214 lines · 0 tokens per session scan A 30b3ac4ff426
fsi-client is a command published in the GitHub repository jovaneyck/fsi-mcp-server (40 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,490 tokens. 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.