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 instructions/milzamsz/flaredeck/agents-mdgit clone --depth 1 https://github.com/milzamsz/flaredeckWrote 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/milzamsz/flaredeck/agents-md)<a href="https://agentmods.dev/instructions/milzamsz/flaredeck/agents-md"><img src="https://agentmods.dev/badge/instructions/milzamsz/flaredeck/agents-md.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 | $0.03154 | $0.03154 |
| Opus 5 | $0.01577 | $0.01577 |
| Sonnet 5 | $0.00631 | $0.00631 |
| Haiku 4.5 | $0.00315 | $0.00315 |
Grade A, and why
flaredeck AGENTS.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 4d 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 — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file applies to the entire flaredeck repository. It is the always-on operating contract for coding agents and human contributors using AI-assisted development.
1. Mission
FlareDeck is a local-first desktop control panel for Cloudflare Tunnel development. The enhancement roadmap adds a trusted local development control plane that can be accessed through the desktop UI, a headless CLI, and a local MCP server.
FlareDeck is not an embedded AI application, a hosted orchestration service, a general-purpose shell runner, or a production deployment platform.
2. Source-of-truth hierarchy
When information conflicts, use this order:
PRODUCT-SCOPE.md- Approved ADRs under
docs/adr/ DOMAIN-MODEL.mdARCHITECTURE.mdTECHNICAL.md- Detailed specifications under
docs/specs/ PLAN.md- Active task specification
- Existing implementation
The existing implementation is evidence of current behavior. It does not automatically override approved architecture. Report conflicts before implementing a material behavior change.
3. Hard invariants
These rules may not be changed without an explicit product decision and approved ADR:
- One profile equals one Cloudflare Tunnel and one API-token identity.
- API tokens are never stored in plaintext and never returned through UI, CLI, MCP, logs, or audit events.
- The existing keychain and encrypted fallback remain the only sanctioned token-write paths.
- Profile creation must verify required access before mutating local or Cloudflare state.
- Ingress configuration preserves the final catch-all
http_status:404rule. - WSL loopback-origin rewriting remains supported.
- Process lifecycle remains platform-aware, including process-tree termination and crashloop protection.
- Desktop, CLI, and MCP interfaces use shared Rust application services.
- The MCP server uses local stdio for the MVP and does not bind a network listener.
- No CLI or MCP operation accepts an arbitrary shell command.
- A workspace runtime may start only from a validated manifest with an active local trust approval for the current fingerprint.
- MCP callers cannot approve workspace trust.
- Stop and cleanup operations are idempotent and ownership-aware.
- New Cloudflare endpoints require scope analysis and actionable error hints.
- Existing updater signing assumptions must not be changed casually.
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.
- 4d ago First seen · 389 lines · 3,154 tokens per session scan A e61606694f18
flaredeck AGENTS.md is an instructions file published in the GitHub repository milzamsz/flaredeck (5 stars, last pushed 9d ago), licensed MIT. It adds 3,154 tokens to every session, about $0.0158 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.