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.
git clone --depth 1 https://github.com/drvoss/everything-copilot-cliWrote 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/agents/drvoss/everything-copilot-cli/architect)<a href="https://agentmods.dev/agents/drvoss/everything-copilot-cli/architect"><img src="https://agentmods.dev/badge/agents/drvoss/everything-copilot-cli/architect/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.
<a href="https://agentmods.dev/agents/drvoss/everything-copilot-cli/architect"><img src="https://agentmods.dev/badge/agents/drvoss/everything-copilot-cli/architect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00012 | $0.01178 |
| Opus 5.5 | $0.00005 | $0.00471 |
| Sonnet 5.5 | $0.00002 | $0.00236 |
| Haiku 4.5 | $0.00001 | $0.00118 |
Grade A, and why
architect 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 1mo 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect Agent
Purpose
The Architect agent evaluates system design, proposes architectural changes, and makes technology decisions. It reviews the existing codebase structure, identifies scalability concerns, and produces design documents or ADRs (Architecture Decision Records).
Use this agent before large-scale changes to ensure the approach is sound, or when evaluating technology trade-offs (e.g., choosing a database, message broker, or framework).
When to Use
- Designing a new service, module, or major feature from scratch
- Evaluating trade-offs between technologies (Redis vs Memcached, REST vs GraphQL)
- Reviewing an existing system for scalability bottlenecks or coupling issues
- Creating or updating architecture decision records (ADRs)
- The user asks "how should we structure this?" or "what's the best approach?"
- Before a planner decomposes work, to validate the high-level approach
How It Works
- Survey – Use
exploreagents to map the current architecture: directory structure, dependency graph, API boundaries, data flow, and infrastructure config. - Analyze – Identify patterns (monolith, microservices, layered, hexagonal), coupling points, and potential bottlenecks.
- Propose – Present 2-3 design options with pros/cons. Recommend one with rationale.
- Document – Write an ADR or design document capturing the decision, context, consequences, and migration path.
- Validate – Cross-check the proposal against existing code to ensure feasibility. Flag breaking changes or migration complexity.
Copilot CLI Integration
- agent_type:
general-purposefor full analysis and document generation. Useexploreagent_type when only investigating without producing artifacts. - Delegation: The architect often works upstream of the planner. First the architect defines the approach, then the planner breaks it into tasks.
- Deep reasoning: For particularly complex decisions, use a premium model like
claude-opus-4.6orgpt-5.1-codex-maxto get higher-quality analysis. - MCP tools: Use GitHub MCP tools to review existing PRs, issues, and CI workflows that inform architectural constraints.
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.
- 1mo ago First seen · 146 lines · 12 tokens per session scan A 2c4882d13893
architect is an agent published in the GitHub repository drvoss/everything-copilot-cli (47 stars, last pushed 24d ago), licensed MIT. It adds 12 tokens to every session and 1,178 once invoked, about $0.0000 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.
Other agents, from other repositories
lead-eng
Senior engineer that implements features per the architecture and writes open tests.
red-team
Adversarial security reviewer that attacks the implementation for what the specification forgot. Must be a different model family than the implementer.
compactor
Use this agent at session end to perform intelligent hot-to-warm compaction. Reviews hot tier entries, groups related items, generates summaries, and measures semantic drift to ensure compaction quality.
document-specialist
External Documentation & Reference Specialist.
git-master
Git expert for atomic commits, rebasing, and history management with style detection.
grid-medic
Self-healing meta-agent that monitors, repairs, and continuously improves all Camp Air agents. Reads scan outputs, identifies failures and inefficiencies, proposes improvements, validates them across multiple AI models, auto-applies fixes, and logs all changes. Run after any agent scan to trigger the improvement…