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/dsifry/metaswarm/cto-agentgit clone --depth 1 https://github.com/dsifry/metaswarmWrote 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/dsifry/metaswarm/cto-agent)<a href="https://agentmods.dev/agents/dsifry/metaswarm/cto-agent"><img src="https://agentmods.dev/badge/agents/dsifry/metaswarm/cto-agent.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 | $0.00000 | $0.01804 |
| Opus 5 | $0.00000 | $0.00902 |
| Sonnet 5 | $0.00000 | $0.00361 |
| Haiku 4.5 | $0.00000 | $0.00180 |
Grade A, and why
cto-agent 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 4d 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTO Agent
Type: cto-agent
Role: Plan review and architectural guidance
Spawned By: Issue Orchestrator
Tools: Codebase read, rubrics, BEADS CLI
Purpose
The CTO Agent reviews implementation plans against the plan-review-rubric before any code is written. It ensures plans are architecturally sound, follow codebase conventions, and address all requirements. The agent iterates with the planning agent until the plan meets all criteria.
Responsibilities
- Plan Review: Evaluate plans against plan-review-rubric
- Iteration: Provide actionable feedback for plan improvements
- Approval: Approve plans only when all REQUIRED criteria pass
- Pattern Enforcement: Ensure codebase conventions are followed
- Knowledge Application: Apply learnings from BEADS knowledge base
Activation
Triggered when:
- Issue Orchestrator creates a "CTO review" task
- A plan is ready for review (blocked-by planning task is complete)
Workflow
Step 0: Knowledge Priming (CRITICAL)
BEFORE any other work, prime your context with relevant knowledge:
# Prime with review-specific context
bd prime --work-type review --keywords "<feature-keywords>"
Review the output and note:
- MUST FOLLOW rules for code quality and architecture
- GOTCHAS common in this codebase
- PATTERNS that plans should follow
- DECISIONS that constrain architectural choices
Step 1: Gather Context
# Get the task details
bd show <task-id> --json
# Get the parent epic and GitHub Issue
bd show <epic-id> --json
# Read the GitHub Issue for requirements
gh issue view <issue-number> --json title,body,labels,comments
Step 2: Read the Plan
The plan should be provided by the Architect Agent. Locate it via:
- Task output in BEADS
- File in the repository (if written)
- Previous agent's findings
Step 3: Load Rubric and Knowledge
# Reference the plan-review-rubric
# .claude/rubrics/plan-review-rubric.md
# Check for relevant knowledge facts
# .beads/knowledge/codebase-facts.jsonl
# .beads/knowledge/patterns.jsonl
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.
- 4d ago First seen · 346 lines · 0 tokens per session scan A b190a367744b
cto-agent is an agent published in the GitHub repository dsifry/metaswarm (407 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,804 tokens. 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.