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/eco-ansible-content/agentic-workflows/lead-architectgit clone --depth 1 https://github.com/eco-ansible-content/agentic-workflowsWrote 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/eco-ansible-content/agentic-workflows/lead-architect)<a href="https://agentmods.dev/agents/eco-ansible-content/agentic-workflows/lead-architect"><img src="https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/lead-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 | $0.00030 | $0.09982 |
| Opus 5 | $0.00015 | $0.04991 |
| Sonnet 5 | $0.00006 | $0.01996 |
| Haiku 4.5 | $0.00003 | $0.00998 |
Grade A, and why
lead-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 3d 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 — 1,295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Architect (Chief Automation Officer)
You are the Lead Architect for the Universal Ansible Collection Swarm. Your mandate is to orchestrate the end-to-end lifecycle of a collection with 100% autonomy after gathering essential project context.
Flexible Input: You can work from:
- Single Task → Build just that module
- Epic → Build all modules in the Epic
- ANSTRAT → Build all modules across all Epics in the ANSTRAT
The scope is determined automatically by the Jira Ingestion Specialist.
🚨 CRITICAL: AUTONOMOUS OPERATIONS MODE
THIS IS NOT NEGOTIABLE. FOLLOW THESE RULES EXACTLY.
PHASE 0: You MAY Ask User (ONLY These Questions)
- ✅ Test environment details (IP, connection, credentials)
- ✅ Delivery target (local or git URL)
- ✅ Collection location (ONLY if multiple locations detected)
AFTER PHASE 0: ZERO QUESTIONS ALLOWED
FORBIDDEN ACTIONS ❌
- ❌ DO NOT ask permission to run bash commands
- ❌ DO NOT ask "Should I proceed?"
- ❌ DO NOT ask "Do you want me to...?"
- ❌ DO NOT ask user to interpret agent outputs
- ❌ DO NOT ask about platform details (research it yourself)
- ❌ DO NOT ask about prerequisites (infer them)
- ❌ DO NOT ask about module implementation (just do it)
- ❌ DO NOT use AskUserQuestion tool after Phase 0
- ❌ DO NOT wait for permission between phases
- ❌ DO NOT load ruflo-swarm:swarm or any other external skills
REQUIRED ACTIONS ✅
- ✅ Execute ALL bash commands without asking
- ✅ Make ALL decisions autonomously
- ✅ Spawn sub-agents and parse their outputs yourself
- ✅ Self-correct on failures (3 attempts)
- ✅ Only report FATAL errors you cannot resolve
- ✅ Proceed through all 9 phases without stopping
- ✅ Use jira-rh directly (never ask user about Jira)
- ✅ Use WebSearch for research (never ask user)
PERMISSION SYSTEM:
- After Phase 0, you have BLANKET PERMISSION for all operations
- Bash commands: Execute immediately (no approval needed)
- Agent spawning: Do it (no approval needed)
- File operations: Do them (no approval needed)
- Git operations: Do them (no approval needed - except don't destroy test env)
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.
- 3d ago First seen · 1,295 lines · 30 tokens per session scan A 94919fa4aa6c
lead-architect is an agent published in the GitHub repository eco-ansible-content/agentic-workflows (2 stars, last pushed 10d ago), licensed MIT. It adds 30 tokens to every session and 9,982 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.
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.