Borrowing it
Nothing to install: this file belongs to shaokeyibb/dsh-plugin-product-subagents. 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/shaokeyibb/dsh-plugin-product-subagents/main/AGENTS.mdgit clone --depth 1 https://github.com/shaokeyibb/dsh-plugin-product-subagentsWrote 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/shaokeyibb/dsh-plugin-product-subagents/agents-md)<a href="https://agentmods.dev/instructions/shaokeyibb/dsh-plugin-product-subagents/agents-md"><img src="https://agentmods.dev/badge/instructions/shaokeyibb/dsh-plugin-product-subagents/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 | $0.00876 | $0.00876 |
| Opus 5 | $0.00438 | $0.00438 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
dsh-plugin-product-subagents 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 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (Claude Code, Codex, DeepSeek Harness agents, …) working in this repository.
What this is
dsh-plugin-product-subagents — a DeepSeek Harness (Cordis) plugin that turns
external agent CLIs (Claude Code, Codex, any ACP agent) into role-based,
continuable subagents: one-shot sync or async continuable, with durable
session recovery, per-role product permissions, and delegation capped by a
permission ceiling.
Commands
npm install # install dependencies
npm test # node:test suite (pure logic + fake bridge; no CLIs/keys)
npm run lint # syntax-check every module (node --check)
Never add tests that require a real product CLI or an API key — the suite must run green on CI (macOS / Ubuntu / Windows × Node 18/20/22) with no credentials.
Repo layout
lib/
index.js # apply(): wires providers, lifecycle, tools
tools/ # one module per model-facing tool
bridges/ # one bridge per product protocol (claude / codex / acp)
providers.js # config-driven provider registry (+ custom ACP agents)
roles.js # role library loader
config.js # zod config validation
registry.js # durable remote-session registry file
run.js # cross-platform process launching (Windows .cmd shims)
availability.js # CLI detection
bindings.js # child→remote binding map + log-marker recovery
progress.js # session-log folding (progress/trace/token usage)
roles/ # declarative role files (*.json)
test/ # node:test suite
docs/ARCHITECTURE.md # bridge contract, permission model, adding products
Design rules (non-negotiable)
- The relay model is always a read-only pipe. A child's toolFilter only
ever contains
product_submitplusproduct_delegatewhen the role allows delegation. Never add a write-capable tool to a child. - Permissions are for the remote product.
permissionMode(readonly/default/full) maps to the product's own CLI flags. - Permissions inherit down the delegation tree. A child cannot spawn a
descendant with a higher
permissionMode— enforced inlib/tools/product-delegate.js(PERM_RANK). - The bridge contract is fixed. Every bridge in
lib/bridges/implementscreate(cwd),submit(remote, task, signal, cwd, settings),reconnect(sessionId, cwd),dispose(remote). Adding a product = a new bridge + a provider entry; a plain ACP CLI needs no code at all (config.providers). - Cross-platform. All CLI launches go through
lib/run.js(spawnProduct/spawnSyncProduct) — they handle Windows.cmdshims. Paths usejoin()andfileURLToPath, never string concatenation orURL.pathname. - Session continuity is layered. Remote session ids are captured as early as possible and durably recorded (binding → registry file → log marker). Do not break the recovery chain.
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.
- 8d ago First seen · 82 lines · 876 tokens per session scan A f4aa1acf0278
dsh-plugin-product-subagents AGENTS.md is an instructions file published in the GitHub repository shaokeyibb/dsh-plugin-product-subagents (20 stars, last pushed 22d ago), licensed MIT. It adds 876 tokens to every session, about $0.0044 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.
Other instructions, from other repositories
data-scientist copilot-instructions.md
Repository instructions for a data-science workflow in GitHub Copilot, covering datasets, statistics, and analysis files.
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.