agentmods.dev

dsh-factory AGENTS.md

Architecture and safety instructions for DSH Factory, a system that stores tasks and workflows, schedules their runs, executes agents, and displays them in a web interface. They describe the separate packages that own storage, scheduling, agent tools, and the user interface.

In plain words
What is it for?
Adding or changing task graphs, recurring schedules, persistence, state transitions, agent execution, model tools, and the React screens that show work and run status.
Why use it?
They prevent duplicate agent loops, tool registries, or state stores from being added in the wrong package. This keeps task history durable and separates backend business rules from interface-only state.

Instructions file for CodexOpenCode

5 5d ago A scan 338 tokens original MIT
View the source file monotykamary/dsh-factory
Install

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.

agentmods
npx agentmods add instructions/monotykamary/dsh-factory/agents-md
Clone the repo
git clone --depth 1 https://github.com/monotykamary/dsh-factory

Made for: Codex, OpenCode.

Per session 338 This file is loaded in full into every session.
When invoked 338 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00338 $0.00338
Opus 5 $0.00169 $0.00169
Sonnet 5 $0.00068 $0.00068
Haiku 4.5 $0.00034 $0.00034

Measured yesterday against content hash 3904b17d680a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dsh-factory 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 yesterday.

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.

AGENTS.md · 27 lines

What it actually says

AGENTS.md

Scope

This repository implements the durable Factory task graph as external DeepSeek Harness plugins. Keep protocol, persistence, scheduling, DSH execution, model tools, and browser presentation in their owning packages.

Architecture

  • dsh-factory-protocol: host-independent task, flow, recurring schedule, run, observation, and graph records.
  • dsh-factory-store: persistence Service Definition.
  • dsh-factory-store-sqlite: transactional document, presence, and scheduler-lease provider.
  • dsh-factory-domain: state transitions and Typert Remote methods.
  • dsh-factory-scheduler: dependency/lane/cron reconciliation and DSH Agent execution.
  • dsh-factory-tools: model tools, explicit run completion, and the bundled Factory skill.
  • dsh-factory-client-ui: Work, task card, all-run Triage, and workspace settings surface.
  • The workspace root is the installable dsh-factory bundle.

Do not introduce a second agent loop, tool registry, session store, or React business store. Factory tasks and flows are durable Factory state; model-visible run input and completion remain logged in DSH Sessions. React owns only filters, selection, expansion, drafts, and viewport state.

Safety

A checkout is one serialized writer lane. Never force-remove a worktree, delete dirty work, or release a lane while shared presence reports a live Session. Publishing remains an explicit task and cleanup cannot rewrite the flow outcome.

Verification

Run pnpm run check. Browser screenshots additionally run pnpm run test:e2e after building the client bundle.

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. yesterday First seen · 27 lines · 338 tokens per session scan A 3904b17d680a

Subscribe to this mod's changes

dsh-factory AGENTS.md is an instructions file published in the GitHub repository monotykamary/dsh-factory (5 stars, last pushed 5d ago), licensed MIT. It adds 338 tokens to every session, about $0.0017 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.

Data and AIDatabasesFrontendai-agentscordisdeepseek-harnessdependency-graphdsh-pluginmulti-agent-systems
Related

Other instructions, from other repositories

dsh-web AGENTS.md

Instructions for zhu1090093659/dsh-web, covering dsh-web repository instructions, repository layout, common commands, repository rules and development workflow.

zhu1090093659/dsh-web · 2,250 tokens

dsh-mcp-panel AGENTS.md

Instructions for PerryLink/dsh-mcp-panel, covering agents.md, layout, hard rules applied here, config and build.

PerryLink/dsh-mcp-panel · 1,748 tokens

dsh-codex-sync AGENTS.md

Instructions for Walvez/dsh-codex-sync, covering agents.md — dsh-codex-sync, 定位, 怎么跑, 技术栈 and 目录与约定.

Walvez/dsh-codex-sync · 666 tokens

dshline AGENTS.md

Instructions for riesbri/dshline, covering agents.md, what this project is, commands, one trap: build before you test by hand and rules that are easy to break.

riesbri/dshline · 5,172 tokens

dsh-industry-research AGENTS.md

Instructions for PerryLink/dsh-industry-research, covering agents.md, layout, hard rules applied here, checks and release.

PerryLink/dsh-industry-research · 1,388 tokens

dsh-mcp-manager AGENTS.md

Instructions for hyqhyq3/dsh-mcp-manager, covering agents.md, layout, architecture rules, commands and conventions.

hyqhyq3/dsh-mcp-manager · 1,189 tokens