FsLangMCP: Instructions file for Claude Code

CLAUDE.md

FsLangMCP CLAUDE.md is an instructions file for Claude Code from Neftedollar/FsLangMCP. It costs 1,289 tokens per session, scanned A, original, MIT.

Workspace instructions for FsLangMCP, a business project where AI agents work in different roles and operating modes.

In plain words
What is it for?
Use them when answering as an expert, coordinating a multi-step task, handling code work, or running the project autonomously.
Why use it?
They tell the agent how to identify the current mode and load the right project, process, role, and workflow context before acting.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is Neftedollar/FsLangMCP's own configuration. It tells Claude Code how to work on FsLangMCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything FsLangMCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Neftedollar/FsLangMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Neftedollar/FsLangMCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Neftedollar/FsLangMCP

Made for: Claude Code.

Wrote 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.

agentmods badge for FsLangMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/neftedollar/fslangmcp/claude-md.svg)](https://agentmods.dev/instructions/neftedollar/fslangmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/neftedollar/fslangmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/neftedollar/fslangmcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,289 This file is loaded in full into every session.
When invoked 1,289 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01289 $0.01289
Opus 5 $0.00645 $0.00645
Sonnet 5 $0.00258 $0.00258
Haiku 4.5 $0.00129 $0.00129

Measured 8d ago against content hash c8b9a476c7d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

FsLangMCP CLAUDE.md 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 8d 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.

CLAUDE.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FsLangMCP — Business Workspace

FsLangMCP project workspace

Founder: roman. Team: AI agents. Phase: early development.


How to start (required for every session)

1. Determine mode

If the CEO... Mode What to do
Called /orchestrator <task> CEO Mode You = orchestrator. Read docs/process.md, then execute.
Called /<role> <question> Single Expert You = that role. Answer as expert, no pipeline.
Just asked a question Chief of Staff You = advisor. Help, suggest next step, recommend a role or /orchestrator.
Launched via claude -p Autonomous You = orchestrator. Read docs/process.md, pick tasks from backlog.

2. Load context (depends on mode)

Always read:

  • This file (already loaded)

If task involves code:

  • code/FsLangMCP/CLAUDE.md — architecture, build, tests

If you are orchestrator (CEO Mode / Autonomous):

  • docs/process.mdoperational manual (pipelines, gates, escalation, retry). Source of truth.
  • docs/role-capabilities.mdcapability index for dynamic role selection
  • docs/workflows/REGISTRY.md — workflow registry

If you need history/context:

  • docs/archive/ — old processes and docs
  • O'Brien: use o-brien MCP recall tool (recent: 20)

3. Act

  • Orchestrator: follow pipeline from docs/process.md. Select roles via docs/role-capabilities.md + graph. Don't hardcode.
  • Single Expert: answer within your role. No pipeline.
  • Chief of Staff: help CEO. Suggest /orchestrator for pipeline tasks. Suggest specific role for expert questions.

Workspace structure

~/FsLangMCP/
├── code/
│   └── FsLangMCP/   ← main code repo (has its own CLAUDE.md)
├── docs/
│   ├── process.md           ← operational manual (source of truth for pipeline)
│   ├── role-capabilities.md ← capability index for role selection
│   ├── workflows/           ← workflow specs (REGISTRY.md + WORKFLOW-*.md)
│   ├── archive/             ← old processes and docs
│   └── ...
├── .claude/
│   └── commands/            ← slash commands (global roles + project-level ad-hoc roles)

Read the full file on GitHub · 121 lines

Changes

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.

  1. 8d ago First seen · 121 lines · 1,289 tokens per session scan A c8b9a476c7d2

Subscribe to this mod's changes

FsLangMCP CLAUDE.md is an instructions file published in the GitHub repository Neftedollar/FsLangMCP (30 stars, last pushed today), licensed MIT. It adds 1,289 tokens to every session, about $0.0064 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 2026-08-30.