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.
git clone --depth 1 https://github.com/Parslee-ai/neoWrote 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/commands/parslee-ai/neo/neo-architect)<a href="https://agentmods.dev/commands/parslee-ai/neo/neo-architect"><img src="https://agentmods.dev/badge/commands/parslee-ai/neo/neo-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/parslee-ai/neo/neo-architect"><img src="https://agentmods.dev/badge/commands/parslee-ai/neo/neo-architect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00060 | $0.00452 |
| Opus 5 | $0.00030 | $0.00226 |
| Sonnet 5 | $0.00012 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
neo-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 11d 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.
What it actually says
Get architectural guidance from Neo on design decisions.
Usage
/neo-architect <your architectural question>
Description
Use this command when you need help making architectural decisions. Neo will analyze tradeoffs, provide confidence scores, and reference similar systems from its memory.
Examples
/neo-architect Should I use microservices or monolith for this project?
/neo-architect What's the best way to handle real-time notifications? WebSockets vs SSE vs polling?
/neo-architect How should I structure a multi-tenant SaaS database?
What Happens
Neo will:
- Analyze tradeoffs between different approaches
- Consider scalability, maintainability, and complexity
- Search memory for similar architectural decisions
- Provide recommendations with confidence scores and risk analysis
Presentation
Invoke with --json and follow the agent's communication protocol
(agents/neo.md). For architecture specifically:
- Lead with
orchestrator.summary, then the recommendation. - Name the alternatives considered and why each lost. An architectural
recommendation without its rejected options is an opinion, not guidance.
hypothesis_rejectedevents and the plan's rationale fields carry this. - State the tradeoff Neo accepted, in the user's terms: what gets harder if they follow this advice.
- Surface
orchestrator.cautionsin full. Architecture mistakes are the expensive kind to reverse. - Be explicit that this is advice, not a decision. Architectural context Neo cannot see — team, timeline, politics — routinely dominates.
Parameters
This command uses advise mode. Architecture guidance is not automatically
promoted into policy or durable architecture memory.
<question>- Your architectural question (required)
Include constraints: scalability needs, team size, infrastructure, timeline
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.
- 11d ago First seen · 64 lines · 60 tokens per session scan A 29dc9a8e492f
neo-architect is a command published in the GitHub repository Parslee-ai/neo (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 60 tokens to every session and 452 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.