Borrowing it
Nothing to install: this file belongs to fieldcure/fieldcure-assiststudio-runner. 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/fieldcure/fieldcure-assiststudio-runner/main/CLAUDE.mdgit clone --depth 1 https://github.com/fieldcure/fieldcure-assiststudio-runnerWrote 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/fieldcure/fieldcure-assiststudio-runner/claude-md)<a href="https://agentmods.dev/instructions/fieldcure/fieldcure-assiststudio-runner/claude-md"><img src="https://agentmods.dev/badge/instructions/fieldcure/fieldcure-assiststudio-runner/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/fieldcure/fieldcure-assiststudio-runner/claude-md"><img src="https://agentmods.dev/badge/instructions/fieldcure/fieldcure-assiststudio-runner/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 | $0.02299 | $0.02299 |
| Opus 5 | $0.01149 | $0.01149 |
| Sonnet 5 | $0.00460 | $0.00460 |
| Haiku 4.5 | $0.00230 | $0.00230 |
Grade A, and why
fieldcure-assiststudio-runner 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 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FieldCure AssistStudio Runner
Windows-only headless LLM task automation engine — define natural language
tasks, schedule them via Windows Task Scheduler, and dispatch results
through the AssistStudio Outbox channels (Slack, Telegram, Email,
KakaoTalk, Discord). Runs as an MCP server in serve mode for task CRUD
and as a one-shot CLI in exec mode for headless execution.
Distributed as a single dotnet tool NuGet package
(FieldCure.AssistStudio.Runner).
Solution structure
FieldCure.AssistStudio.Runner.slnx ← .slnx format (requires VS 17.12+)
src/
└── FieldCure.AssistStudio.Runner/ → NuGet: FieldCure.AssistStudio.Runner
│ (net8.0, [SupportedOSPlatform("windows")])
│ PackAsTool=true, ToolCommandName=assiststudio-runner
│ PackageType=McpServer (.mcp/server.json)
│
├── Program.cs Entry point — dispatches `serve` / `exec` /
│ `config` subcommands.
├── Configuration/ConfigRunner.cs `config init / set-credential / get-credential` CLI.
├── Credentials/ PasswordVault adapter (Windows Credential Manager).
│ ├── ICredentialService GetApiKey / SetApiKey + GetMcpEnvVar / SetMcpEnvVar.
│ └── CredentialService Single-user CredWrite/CredRead implementation.
├── Execution/
│ ├── TaskExecutor Task → AgentLoop run, streams ExecutionLog rounds.
│ └── McpServerPool Bootstraps task-scoped MCP servers + tool allowlist.
├── Models/
│ ├── RunnerConfig Global runner.json shape: DefaultModelName, Models
│ │ (Dictionary<string, ModelConfig>), DefaultMcpServers,
│ │ Retry, FallbackChannel, …
│ ├── RunnerTask Task DB row: prompt, schedule, ModelName, Guardrails,
│ │ McpServers, OutputChannel.
│ ├── TaskExecution Per-run execution record with status + summary.
│ ├── ExecutionLog Round-by-round trace for audit (Messages array).
│ ├── ExecutionStatus Pending / Running / Succeeded / Failed / Cancelled / TimedOut.
│ └── McpServerConfig Task-level MCP server entry (id/name/command/args/env-keys).
├── Scheduling/
│ ├── IJobScheduler Abstraction so future non-Windows backends can plug in.
│ ├── WindowsTaskScheduler Default implementation — schtasks shell-out.
│ ├── SchtasksTrigger Encodes a schedule as schtasks command-line arguments.
│ └── CronToSchtasks Cron expression → schtasks subset (5-field standard cron).
├── Storage/TaskStore.cs SQLite (`runner.db`) — Tasks + TaskExecutions tables,
│ inline ALTER TABLE migrations on Initialize().
├── Tools/ MCP tool implementations (one per file).
│ ├── CreateTaskTool / UpdateTaskTool / DeleteTaskTool
│ ├── ListTasksTool / GetTaskHistoryTool / GetExecutionStatusTool
│ └── RunTaskTool Triggers a task and optionally waits up to 60s.
├── .mcp/server.json MCP registry metadata (mirrors csproj <Version>).
├── README.md NuGet-shipped package README.
└── Logo.png Package icon.
tests/
└── FieldCure.AssistStudio.Runner.Tests/ RunnerConfigTests + others (MSTest).
scripts/publish-nuget.ps1 Pack → sign (GlobalSign EV USB dongle) → push.
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 · 177 lines · 2,299 tokens per session scan A 03e59a6649d9
fieldcure-assiststudio-runner CLAUDE.md is an instructions file published in the GitHub repository fieldcure/fieldcure-assiststudio-runner (1 stars, last pushed 3mo ago), licensed MIT. It adds 2,299 tokens to every session, about $0.0115 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.