Borrowing it
Nothing to install: this file belongs to YingSuiAI/dirextalk-deployer. 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/YingSuiAI/dirextalk-deployer/main/AGENTS.mdgit clone --depth 1 https://github.com/YingSuiAI/dirextalk-deployerWrote 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/yingsuiai/dirextalk-deployer/agents-md)<a href="https://agentmods.dev/instructions/yingsuiai/dirextalk-deployer/agents-md"><img src="https://agentmods.dev/badge/instructions/yingsuiai/dirextalk-deployer/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 5.1 | $0.03077 | $0.03077 |
| Opus 5 | $0.01538 | $0.01538 |
| Sonnet 5 | $0.00615 | $0.00615 |
| Haiku 4.5 | $0.00308 | $0.00308 |
Grade A, and why
dirextalk-deployer AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Deployer execution paths** are used by the orchestration engine. On Git Bash, normalize paths before passing them to Windows-native Node.js, AWS CLI, curl, or agent executables. Do not rely on implicit MSYS argv conv How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
dirextalk-deployer is a cross-platform deployment product and agent skill, not a Linux-only script collection. Maintain it as a portable orchestration layer driven by Git Bash on native Windows and Bash on Linux/macOS/WSL while deploying a Linux-based Dirextalk server.
Development
- This vNext repository is being built from zero. Implement the best target contract directly. Do not retain historical-version compatibility code.
- Do not add dual paths, version negotiation, compatibility shims, or fallback branches for superseded designs. Replace the old contract and migrate test or development data directly; a frozen external boundary requires an explicit product decision, not a second production path.
- Prioritize core product behavior and real device/node evidence. Do not add anti-counterfeit or exhaustive adversarial-observer machinery beyond the required release provenance unless a concrete product threat or gate needs it.
- Review the final production path strictly; model and fixture tests do not substitute for executable integration evidence.
Product Scope
- Deploy, resume, verify, destroy, and locally wire a production Dirextalk message server.
- Install the independently released
YingSuiAI/dirextalk-updaterhost binary from the deployer-owned immutable version/commit/SHA pin. The deployer does not embed or build updater Go source. - Own the production split Compose topology, host lifecycle and image-update
wrappers under
scripts/cloud-init/split/runtime, together with their operational tests and canonical bundle. Message Server and Agent repositories own only their application image builds and formal version-tag publication. - Fresh deployment installs the updater control plane with its resident watchdog disabled. Direct-version upgrades are client initiated; do not reintroduce the retired daily updater GitHub discovery timer or service.
- Treat
SKILL.mdas the compact agent-facing entrypoint. Detailed runbooks belong inreferences/;scripts/are the stable implementation entrypoints. SKILL.mdis a user-facing runbook that must remain usable by less capable models. Its Freshness Gate, step-by-step onboarding, semantic confirmation policy, AWS promotional/billing reminders, and repeated safety guidance are intentional product behavior; preserve them unless the product owner explicitly changes that onboarding contract.- The supported local conversation bridge is
dirextalk-connect, installed fromdirextalk-connect@latestby default or built fromYingSuiAI/dirextalk-connect. - MCP support is capability-driven and is separate from bridge-agent support. Declared MCP consumers connect directly to the deployed message server's HTTP endpoint; unknown runtimes never receive a generic fallback.
- Supported local agent targets are the dirextalk-connect agent providers, treated as peers:
acp,antigravity,claudecode,codex,copilot,cursor,devin,gemini,iflow,kimi,opencode,pi,qoder,reasonix, andtmux. - Do not reintroduce legacy local gateway installation flows or third-party chat platform wiring.
- Do not hard-code one developer's home directory, shell, agent executable path, AWS region, domain, node id, token, or password.
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 · 143 lines · 3,077 tokens per session scan A 1303cf8a3268
dirextalk-deployer AGENTS.md is an instructions file published in the GitHub repository YingSuiAI/dirextalk-deployer (457 stars, last pushed 6d ago), licensed MIT. It adds 3,077 tokens to every session, about $0.0154 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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.