Borrowing it
Nothing to install: this file belongs to panzeyu2013/dsh-chamber. 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/panzeyu2013/dsh-chamber/main/AGENTS.mdgit clone --depth 1 https://github.com/panzeyu2013/dsh-chamberWrote 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/panzeyu2013/dsh-chamber/agents-md)<a href="https://agentmods.dev/instructions/panzeyu2013/dsh-chamber/agents-md"><img src="https://agentmods.dev/badge/instructions/panzeyu2013/dsh-chamber/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 | $0.05137 | $0.05137 |
| Opus 5 | $0.02568 | $0.02568 |
| Sonnet 5 | $0.01027 | $0.01027 |
| Haiku 4.5 | $0.00514 | $0.00514 |
Grade A, and why
dsh-chamber 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 2d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dsh-chamber Agent Guide
Purpose
dsh-chamber is primarily the local desktop connection manager for dsh: the local dsh instance (web profile) is hosted by the control plane; dsh instances on remote servers are attached over SSH tunnels. The UI is the dsh official frontend, source-reused and self-built (single window, single frame; multiple instances coexist as N-ctx shells). The control plane owns connection management, per-instance same-origin reverse proxying, and static frontend serving (the desktop v1 control plane has no authentication/audit surface and remains loopback-only). Host-native capabilities (goals, jobs, terminals, settings, pluginInventory, …) remain the host and host-frontend's job — the control plane only attaches, never re-implements. Session business is entirely the dsh frontend runtime's job; the desktop control plane consumes no host frames.
Design 17 adds a second, explicitly invoked server deployment shape in packages/gateway. It composes the same local-host manager behind an authenticated-by-default public request boundary; the explicit, loudly warned --no-auth override is a bounded trusted-network exception and never a silent fallback. Gateway is never auto-started or imported by the anonymous desktop control plane. 2026-12 (user decision): the gateway orchestration surface was stripped entirely — approvals/questions stay native to dsh (the official frontend handles them), the cross-session scheduler, session index, server-side Git worktree records and feature switches no longer exist; the gateway is a shell (auth + reverse proxy) plus its host duties (design 18 §9 runtime management, credential panel) plus a seed registry: the chamber host packages (dsh-host-client-graph, dsh-host-git-worktree) are desktop-synced via PUT /chamber/plugins into <stateDir>/chamber-plugins/ and seeded into the managed dsh profile at every spawn (version-locked to the connecting desktop; the activation probe skips the chamber host domains until a sync exists — hostDomains/probeExpectedNames), while dsh-chamber-client-ui-mobile is the single packaged exception (mobile access is bound to the gateway and has no desktop in the chain). The gateway never consumes session content and never becomes authoritative for dsh facts. This is a bounded product-shape exception, not permission to move those domains into packages/control-plane or the desktop renderer.
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.
- 2d ago Changed · +6 tokens per session d9f2e606a4d8
- 3d ago Changed · +1 lines · +577 tokens per session cc833cb38f62
- 7d ago First seen · 96 lines · 4,554 tokens per session scan A a2b60ef5e8df
dsh-chamber AGENTS.md is an instructions file published in the GitHub repository panzeyu2013/dsh-chamber (11 stars, last pushed yesterday), licensed MIT. It adds 5,137 tokens to every session, about $0.0257 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
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).
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.
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).
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.