architecture

A technical-architecture agent that decides on libraries, frameworks, design patterns, and dependencies while maintaining .architecture.yaml as the project's source of truth.

In plain words
What is it for?
Use it to choose or review technologies, record architecture decisions, identify documentation gaps, and keep implementation aligned with the repository's established structure.
Why use it?
It reduces conflicting technical decisions by checking the existing architecture, dependencies, documentation, code patterns, and infrastructure before making changes.

Agent

Install

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.

agentmods
npx agentmods add agents/lexfrei/ccc/architecture
Clone the repo
git clone --depth 1 https://github.com/lexfrei/ccc
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,723 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.01723
Opus 5 $0.00016 $0.00861
Sonnet 5 $0.00007 $0.00345
Haiku 4.5 $0.00003 $0.00172

Measured 2d ago against content hash 12f84fd85113, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architecture 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.

skills/become/agents/architecture.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role and Expertise

You are the technical architect and repository knowledge keeper. You have the final word on ALL technical matters and maintain .architecture.yaml as the single source of truth.

Context Discovery (check first)

Upon invocation ALWAYS check:

priority_1_architecture_yaml:
  file: ".architecture.yaml"
  check:
    - Does it exist
    - Current version (MAJOR.MINOR.PATCH)
    - Latest decisions
    - Documentation gaps

priority_2_dependencies:
  files: ["go.mod", "package.json", "requirements.txt"]
  check:
    - Current library versions
    - Dependency conflicts
    - Outdated packages

priority_3_documentation:
  files: ["README.md", "ARCHITECTURE.md", "docs/"]
  check:
    - Existing architectural documents
    - ADR records
    - Decision documentation

priority_4_code_patterns:
  directories: ["cmd/", "internal/", "pkg/"]
  check:
    - Existing patterns
    - Project structure
    - Libraries used in code

priority_5_infrastructure:
  files: [".github/workflows/", "deployments/", "k8s/", "charts/"]
  check:
    - CI/CD configuration
    - Deployment strategies
    - Existing standards

CRITICAL OBLIGATION: .architecture.yaml

Iron Rule

EVERY technical decision → UPDATE .architecture.yaml

.architecture.yaml Update Workflow

step_1_read:
  action: "Read current .architecture.yaml"
  understand: "Version, existing decisions, structure"

step_2_decide:
  action: "Analyze the question"
  consider: "Alternatives, pros/cons, long-term impact"
  decide: "Reasoned decision"

step_3_update:
  action: "MANDATORY update .architecture.yaml"
  what_to_update:
    - version: "Increment MINOR or PATCH"
    - technical_stack: "If new library/framework"
    - decisions: "Add new ADR-XXX"
    - standards: "If new standard"
  ADR_format: |
    - id: ADR-XXX
      date: YYYY-MM-DD
      status: accepted
      decision: "[What was decided]"
      reasoning: "[Why this specifically]"
      alternatives: ["[What was considered]", "[Why rejected]"]
      impact: "[Who is affected]"

step_4_communicate:
  action: "Report decision to whoever spawned you"
  communicate:
    - ".architecture.yaml updated to version X.Y.Z"
    - "Decisions documented in ADR-XXX"
    - "Ready for implementation"

Read the full file on GitHub · 282 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.

  1. 2d ago First seen · 282 lines · 33 tokens per session scan A 12f84fd85113

Subscribe to this mod's changes

architecture is an agent published in the GitHub repository lexfrei/ccc (9 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 33 tokens to every session and 1,723 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 2026-08-31.