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 skills/hashlips/agent-skills/capability-architecturenpx skills add HashLips/agent-skills --skill capability-architecturegit clone --depth 1 https://github.com/HashLips/agent-skillsWrote 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/hashlips/agent-skills/capability-architecture)<a href="https://agentmods.dev/skills/hashlips/agent-skills/capability-architecture"><img src="https://agentmods.dev/badge/skills/hashlips/agent-skills/capability-architecture.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 | $0.00077 | $0.00919 |
| Opus 5 | $0.00039 | $0.00460 |
| Sonnet 5 | $0.00015 | $0.00184 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
capability-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 6d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capability Architecture
Design systems that remain adaptable, modular, and maintainable by organizing software around capabilities, boundaries, contracts, and layered responsibilities.
Core Rules
Always separate:
- what the system does
- how it is displayed
- how it is stored
- how it is called
This keeps business logic portable and prevents tight coupling to frameworks, transport, and infrastructure.
Workflow
When designing or refactoring architecture:
- Identify business capabilities
- Define module boundaries per capability
- Establish explicit contracts between modules
- Define security and trust boundaries per capability (identity, authorization, sensitive data, validation)
- Define observability boundaries per capability (logs, metrics, traces, correlation)
- Assign responsibilities by layer
- Isolate external systems behind adapters
- Prevent cross-layer and cross-module leakage
- Compose the system from capability modules
Non-Negotiable Rules
- Organize by capabilities, not technical artifact type.
- Keep dependency direction inward toward domain logic.
- Keep presentation and transport layers thin.
- Keep infrastructure replaceable through adapters.
- Communicate between modules through contracts only.
- Introduce shared abstractions only after reuse is proven.
- Enforce authorization at capability entry points, not only one outer transport layer.
- Validate untrusted input at trust boundaries; keep domain/application logic on safe explicit inputs.
- Classify sensitive data and secrets; keep secret handling in infrastructure, not domain rules.
- Define capability-level observability signals at entry, success, and failure boundaries.
- Keep logs structured and safe with correlation context and without secret leakage.
Output Contract
Architectures produced with this skill should:
- Define clear capability ownership.
- Define boundaries and contracts for interactions.
- Show explicit layer responsibility split.
- Avoid framework/database leakage into domain logic.
- Document known anti-pattern risks and mitigations.
- State trust boundaries, authorization expectations, and sensitive data handling per capability where relevant.
- Define observability expectations (events, metrics, trace points, correlation IDs) per capability where relevant.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/anti-patterns.md 2.5 KB
- references/architecture-principles.md 1.7 KB
- references/boundary-contracts.md 602 B
- references/capability-modules.md 762 B
- references/coupling-rules.md 534 B
- references/implementation-process.md 845 B
- references/layering-model.md 1.0 KB
- references/observability.md 1.4 KB
- references/reuse-guidelines.md 429 B
- references/security.md 2.5 KB
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.
- 6d ago First seen · 87 lines · 77 tokens per session scan A 8c3506df8339
capability-architecture is a skill published in the GitHub repository HashLips/agent-skills (24 stars, last pushed 11d ago), licensed MIT. It adds 77 tokens to every session and 919 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…