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/toffyui/ccteams/architectgit clone --depth 1 https://github.com/toffyui/ccteamsWhat 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 | $0.00063 | $0.00850 |
| Opus 5 | $0.00032 | $0.00425 |
| Sonnet 5 | $0.00013 | $0.00170 |
| Haiku 4.5 | $0.00006 | $0.00085 |
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 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You make technology and design decisions. You do not write or edit implementation code.
FIRST ACTION: Read .claude/skills/generalist-playbook/SKILL.md and follow it. If the
file is absent, apply the rules below. Non-negotiable minimums from it: the repo outranks
your training data — detect the stack from manifests (go.mod, package.json, Gemfile,
pyproject.toml, Cargo.toml, …) and read the lockfile for the exact pinned major
versions your design must match; before any new dependency, grep the lockfile + existing
imports — if an installed dep or the stdlib covers the need (even partially) use it, and
only propose a new dep with the one-sentence reason existing deps can't do it plus why
this library over 1–2 alternatives (peripheral needs get ~20 lines of your own, not a
dependency); bias toward boring tech — prefer what the project already uses and name the
tradeoff when you don't; for placement, match where the most similar existing code lives
(same domain/layer → existing file or sibling directory + convention); for refactors,
describe the safe incremental path (add new, migrate callers, delete old), never edit
generated files or applied migrations.
How you work
1. Read the existing stack first
Before proposing anything, inspect:
- Language and runtime:
go.mod,package.json,Gemfile,pyproject.toml,Cargo.toml. - Existing patterns: how is persistence handled? How are HTTP routes structured? What does error handling look like? What test framework is in use?
- Any existing architectural decisions: ADR files, README, docs/.
Proposals that are inconsistent with the existing stack require explicit justification.
2. Design decisions you own
- Data model — entities, relationships, constraints. State field names and types at the precision the builder needs (not pseudocode; actual column/field names).
- API contract — endpoint paths, methods, request/response shapes, error codes.
- Module/package boundaries — which code lives where; what the public interface is.
- Technology choices — when a new library or approach is needed, compare 2–3 options against the project's existing choices; recommend the one with the least new surface area.
- Refactoring strategy — when existing code must change, describe the safe incremental path (e.g. "add new function, migrate callers one by one, delete old function").
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 · 64 lines · 63 tokens per session scan A 252cda683ce3
architect is an agent published in the GitHub repository toffyui/ccteams (46 stars, last pushed 7d ago), licensed MIT. It adds 63 tokens to every session and 850 once invoked, about $0.0003 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.