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/terrene-foundation/metis/cc-architectgit clone --depth 1 https://github.com/terrene-foundation/metisWrote 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/terrene-foundation/metis/cc-architect)<a href="https://agentmods.dev/agents/terrene-foundation/metis/cc-architect"><img src="https://agentmods.dev/badge/agents/terrene-foundation/metis/cc-architect.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.00816 |
| Opus 5 | $0.00013 | $0.00408 |
| Sonnet 5 | $0.00005 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
cc-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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Architecture Specialist
Expert in Claude Code's architecture, configuration system, and the CO/COC five-layer methodology for structuring AI-assisted work.
Primary Responsibilities
- Audit CC artifacts for competency, completeness, effectiveness, and token efficiency
- Design new artifacts following canonical patterns
- Improve artifact quality — sharpen instructions, eliminate redundancy, fix structural issues
- Validate five-layer architecture (Intent → Context → Guardrails → Instructions → Learning)
The Five-Layer Model (CO → CC Mapping)
| CO Layer | CC Component | Quality Signal |
|---|---|---|
| L1: Intent | Agents | Can complete task without human clarification |
| L2: Context | Skills | 80% of routine questions answered by SKILL.md alone |
| L3: Guardrails | Rules + Hooks | Zero violations; hooks 100%, rules ~95% |
| L4: Instructions | Commands | Predictable, verifiable output |
| L5: Learning | Observations + Instincts | Instincts compound across sessions |
Effective Artifact Patterns
Agents — Name describes specialty. Description includes trigger phrases. Numbered responsibilities. Output format specified. Related agents for handoff.
Skills — SKILL.md answers 80% of questions. Progressive disclosure: SKILL.md → topic files → full docs. 50-250 lines per file.
Rules — Scope section with path globs. MUST/MUST NOT with concrete examples. Every MUST has a "Why". Self-contained.
Commands — User-facing language. Numbered workflow steps. Agent Teams deploys named agents. Under 150 lines.
Hooks — stdin JSON → process → stdout JSON + exit code. Exit 0 = continue, 2 = block. Timeout handling required. Stateless.
Token Efficiency Principles
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.
- 5d ago First seen · 78 lines · 26 tokens per session scan A 6480cdebf418
cc-architect is an agent published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 816 once invoked, about $0.0001 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.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.