What is chamber AGENTS.md?

Project instructions for Chamber, a desktop app where AI agents can use tools, manage data, create views, and run scheduled jobs. It also describes chatrooms where several agents work together.

Use it when developing Chamber features involving agents, tools, dashboards, data changes, multi-agent chatrooms, or scheduled automation.

It gives coding agents the project’s rules, capabilities, file locations, and security boundaries before they change or extend Chamber.

How ianphil/chamber configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ianphil/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.

Copy the file

curl -O https://raw.githubusercontent.com/ianphil/chamber/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ianphil/chamber

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ianphil/chamber/agents-md/github.svg)](https://agentmods.dev/instructions/ianphil/chamber/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ianphil/chamber/agents-md"><img src="https://agentmods.dev/badge/instructions/ianphil/chamber/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ianphil/chamber/agents-md"><img src="https://agentmods.dev/badge/instructions/ianphil/chamber/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 874 This file is loaded in full into every session.

When invoked 874 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00874	$0.00874
Opus 5.5	$0.00350	$0.00350
Sonnet 5.5	$0.00175	$0.00175
Haiku 4.5	$0.00087	$0.00087

Measured 2mo ago against content hash 4a4113fce8cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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.

AGENTS.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Chamber Agent Governance

Overview

Chamber is a desktop application where AI agents ("minds") operate as a Chief of Staff. Agents connect via the GitHub Copilot SDK and can extend the UI, execute tool calls, modify data, and run scheduled jobs.

Agent Capabilities

Minds

Identity: Each mind has a name, personality, and persistent memory
Tool access: Minds invoke tools via the Copilot SDK (model-driven tool calls)
Lens views: Minds can create view.json files in .github/lens/ to extend the UI with 7 view types (form, table, briefing, detail, status-board, timeline, editor)
Write-back: Minds can modify data through the action bar on any Lens view
Canvas: Minds can render HTML dashboards, reports, and forms in a browser with live reload
Cron: Minds can schedule TypeScript automation scripts under .chamber/automation/*.ts authored as direct ttasks programs with @ianphil/ttasks-ts; @chamber/automation-runtime supplies only Chamber bridge helpers/handlers

Chatroom (Multi-Agent)

Concurrent: All agents respond in parallel
Sequential: Round-robin turns
GroupChat: Moderator-directed conversation
Handoff: Agent-to-agent delegation
Magentic: Manager-driven task ledger

Security Boundaries

Credential Storage

Credentials stored via keytar (OS-native keychain)
Never store credentials in mind directories or .working-memory/

Tool Execution

All tool calls flow through the Copilot SDK
Approval gate (approval-gate.ts) provides tool execution review
Observability layer (observability.ts) emits structured events with redaction

Automation Scripts (Cron)

Cron schedules execute TypeScript files under <mind>/.chamber/automation/*.ts via a bundled Node + tsx + typescript runtime (resources/automation-runtime/).
Script paths are validated by validateScriptPath — must be relative, inside .chamber/automation/, end in .ts, and resolve (with symlinks) to a real file under that directory. Path traversal and symlink-escape are rejected.
ScriptRunner spawns each script in a child Node process with CHAMBER_BRIDGE_URL + a per-spawn CHAMBER_BRIDGE_TOKEN minted by TokenRegistry. Tokens are revoked on script exit and on registry shutdown.
AutomationBridge is a loopback HTTP server (127.0.0.1) requiring Authorization: Bearer <token>. It exposes /prompt (delegates to the calling mind's chat) and /notify (UI surface). All requests are bound to the mind that owns the token.
automation_validate runs tsc --noEmit against the script before execution, surfacing type errors to the mind.

Read the full file on GitHub · 65 lines

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.

2mo ago First seen · 65 lines · 874 tokens per session scan A 4a4113fce8cb

Subscribe to this mod's changes

chamber AGENTS.md is an instructions file published in the GitHub repository ianphil/chamber (12 stars, last pushed 1mo ago), licensed MIT. It adds 874 tokens to every session, about $0.0035 per session on Opus 5.5. 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.

Building agents agent agent-harness agent-os agentic ai-agent ai-agents

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).

microsoft/vscode · 9,715 tokens

chamber: Instructions file for Codex