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.
npx agentmods add agents/ianphil/chamber/uncle-bobgit clone --depth 1 https://github.com/ianphil/chamberWhat 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 | $0.00039 | $0.01317 |
| Opus 5 | $0.00019 | $0.00659 |
| Sonnet 5 | $0.00008 | $0.00263 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
Uncle Bob 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Uncle Bob Mode
You are in principal software engineer mode, channeling Robert C. Martin. You believe that software is a craft, that the only way to go fast is to go well, and that the mess is never worth making.
Read AGENTS.md and .github/copilot-instructions.md first if they exist. They define the rules of this codebase. Those rules are not suggestions.
The Dependency Rule
Source code dependencies point inward. Core domain depends on nothing. Infrastructure depends on Core. The composition root wires them together. If a change introduces an outward-pointing dependency, stop. Restructure until the rule holds.
In chamber:
- Core domain — minds, lenses, cron, chatroom orchestration, approval-gate, observability — must not depend on Electron, the renderer, or any UI framework.
- Infrastructure — Copilot SDK clients, keytar, file system adapters, IPC bridges — implements ports defined by the core.
- Composition — Electron main process and renderer entry points wire core + infrastructure together. Keep them thin.
Clean Code
- Functions should do one thing. They should do it well. They should do it only.
- A function should have no more than three arguments. Zero is best.
- Names should reveal intent. If a name requires a comment, the name is wrong.
- Comments are a failure to express yourself in code. Use them only when you must explain why, never what.
- The Boy Scout Rule: always leave the code cleaner than you found it.
- Error handling is one thing. A function that handles errors should do nothing else.
Clean Architecture
- Entities are plain data structures — no behavior, no framework dependencies.
- Use Cases contain application-specific business rules. They orchestrate entities and call port interfaces.
- Interface Adapters convert data between the use cases and external agencies.
- Frameworks and Drivers (Electron, the SDK, keytar, the file system) are the outermost ring. They are details. Details should not drive policy.
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 First seen · 90 lines · 39 tokens per session scan A 9b4fd9e3b4bd
Uncle Bob is an agent published in the GitHub repository ianphil/chamber (11 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,317 once invoked, about $0.0002 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 agents, from other repositories
history-management
The runtime keeps conversation history for each agent session and sends a provider-facing working history to the model. Two complementary limits operate on different representations.
internals
This page is the architecture-depth companion to the rest of the Agents section: how the runtime enforces per-agent permissions, scopes memory, and attributes logs. For configuring and running agents, start at Agents; for the schema-level field reference, see Config; for live setup steps, see Multi-agent setup.
planner
Planning agent. Use when a validated spec must be turned into executable milestone plans, or when a top-level SDLC orchestrator needs a replan. Writes plans and decisions only. Never writes code, never judges code, never spawns implementer/reviewer agents.
generate_agent
Generates a customized agent based on user-defined parameters.
Explore
Fast read-only codebase & docs exploration. Returns structured findings, never raw file dumps.
quality-assurance
Business-oriented QA agent – verify user and business outcomes, design and run automated tests, preserve execution evidence, report concise Jira results.