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/phuonghx/aim-cli/architecturenpx skills add phuonghx/aim-cli --skill architecturegit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00076 | $0.00629 |
| Opus 5 | $0.00038 | $0.00315 |
| Sonnet 5 | $0.00015 | $0.00126 |
| Haiku 4.5 | $0.00008 | $0.00063 |
Grade A, and why
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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Making Architecture Decisions
Three ideas anchor everything below:
- Requirements come first. The shape of the system follows from what it actually needs to do.
- Trade-offs justify choices. No option is free; name the cost before committing.
- Decision records preserve the "why". Future maintainers inherit the reasoning, not just the result.
Read Only What the Task Needs
This skill is split across several reference files. Don't load all of them. Look at the map, decide what the current request calls for, and open just those.
| File | What it holds | Open it when |
|---|---|---|
context-discovery.md |
The questions to ask up front and a way to classify the project | You're at the very start of a design |
trade-off-analysis.md |
Templates for decision records plus a method for weighing options | You're capturing a decision in writing |
pattern-selection.md |
Branching guides for picking patterns and a list of traps to avoid | You're deciding which pattern fits |
examples.md |
Three fully worked designs (MVP, SaaS, enterprise) | You want a concrete reference to compare against |
patterns-reference.md |
A compact catalog of patterns side by side | You need a fast lookup or comparison |
Companion Skills
Architecture touches neighboring concerns. Hand off to these where they fit:
| Skill | Reach for it when |
|---|---|
@[skills/database-design] |
The decision is about how to model and structure data |
@[skills/api-patterns] |
The focus shifts to designing the API surface |
@[skills/deployment-procedures] |
You're working out how the system ships and runs |
The Guiding Principle
Begin with the smallest design that works, and let complexity earn its place.
- Default to the simple option.
- Reach for heavier patterns only after a real need shows up — not in anticipation of one.
- Layering a pattern on later is straightforward.
- Tearing one out once code depends on it is painful. Adding is cheap; removing is expensive.
What ships with it
5 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.
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.
- yesterday First seen · 63 lines · 76 tokens per session scan A a8bf51c20b9e
architecture is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 629 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 2026-08-31.
Other skills, from other repositories
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
user-persona
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).