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 skills add bikeread/promethos --skill choose-agent-architecturegit clone --depth 1 https://github.com/bikeread/promethosWrote 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/skills/bikeread/promethos/choose-agent-architecture)<a href="https://agentmods.dev/skills/bikeread/promethos/choose-agent-architecture"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/choose-agent-architecture/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/skills/bikeread/promethos/choose-agent-architecture"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/choose-agent-architecture.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 | $0.00029 | $0.00658 |
| Opus 5.5 | $0.00012 | $0.00263 |
| Sonnet 5.5 | $0.00006 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
choose-agent-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 2mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Choose a clear agent architecture that fits the requirements without adding unnecessary complexity.
Inputs
- Approved requirements brief
- Available tools and runtime constraints
- Existing implementation, if any
Non-Goals
- Producing a full implementation plan
- Defaulting to multi-agent patterns for status or novelty
Workflow
Trigger signals
- Requirements are pinned down but no architecture exists yet
- User asks "要几个 agent" or "should this be one agent or many"
- Tools and memory needs are listed but not assigned to components
- An existing agent is being refactored because its boundaries are wrong
1. Restate the architectural pressure
Summarize the requirement forces that actually matter: tool use, planning
complexity, long-running work, memory needs, approval boundaries, or delegation.
If the job, beneficiary, or success bar is still unclear, stop and send the
work back to define-agent-requirements instead of smuggling requirement work
into the architecture step.
Success criteria: The architecture discussion is anchored in explicit design
pressure instead of generic agent buzzwords.
2. Map the smallest viable responsibility slices
Identify the minimum set of responsibilities the system must carry well, such as planning, execution, memory access, verification, or orchestration. Success criteria: The problem is decomposed into a small number of non-overlapping responsibilities.
3. Compare 2-3 viable shapes
Evaluate candidate shapes such as a single tool-using agent, a layered agent with helper modules, or a delegated multi-agent design. Reject options that add complexity without solving a real pressure. Success criteria: There is a recommended shape and explicit reasons the alternatives were not selected.
4. Define boundaries and interfaces
Describe the major components, what each component owns, and what information or artifacts move across boundaries. Success criteria: A future implementation plan can name concrete files or modules without inventing new responsibilities.
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.
- 2mo ago First seen · 81 lines · 29 tokens per session scan A c31eab54b563
choose-agent-architecture is a skill published in the GitHub repository bikeread/promethos (33 stars, last pushed 7mo ago), licensed MIT. It adds 29 tokens to every session and 658 once invoked, about $0.0001 per session on Opus 5.5. 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.
choose-agent-architecture compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| choose-agent-architecturebikeread/promethos | Skill | 33 | 7mo ago | MIT | A | 29 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |