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 endorphin-ai/hasbrains-agent-kit --skill system-architecturegit clone --depth 1 https://github.com/endorphin-ai/hasbrains-agent-kitWrote 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/endorphin-ai/hasbrains-agent-kit/system-architecture)<a href="https://agentmods.dev/skills/endorphin-ai/hasbrains-agent-kit/system-architecture"><img src="https://agentmods.dev/badge/skills/endorphin-ai/hasbrains-agent-kit/system-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/endorphin-ai/hasbrains-agent-kit/system-architecture"><img src="https://agentmods.dev/badge/skills/endorphin-ai/hasbrains-agent-kit/system-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 | $0.00204 | $0.01088 |
| Opus 5.5 | $0.00082 | $0.00435 |
| Sonnet 5.5 | $0.00041 | $0.00218 |
| Haiku 4.5 | $0.00020 | $0.00109 |
Grade A, and why
system-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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TASKLANG TYPE SKILL
IDENTITY "System Architecture"
General-purpose system-design knowledge for the planning step that comes BEFORE technology-specific mechanics: pick the right architecture PATTERN, make the load-bearing TECHNOLOGY decisions, and run the system-design WORKFLOWS (capacity, API, schema, scalability, migration). This skill is a lean MAP — the substance lives in three reference docs under references/. Read the map, then open the one reference that matches the question.
!!! References FIRST — this SKILL.md only routes; the answers live in references/. !!! This is technology-AGNOSTIC system design. Framework-specific mechanics — !!! this stack's module/context boundaries, its ORM schema and migration syntax, !!! its background-job and authorization APIs — belong to a stack-specific skill. !!! system-architecture supports the PLANNING that precedes those mechanics.
When to use this skill
KNOWLEDGE USE_WHEN - "Choosing an architecture pattern for a new system or a milestone (and weighing its trade-offs)." - "Making a technology decision — database, cache, message queue, auth, frontend framework, cloud provider, API style." - "Running a system-design workflow — capacity planning, API design, schema design, scalability assessment, migration planning." - "Doing the PLAN-FIRST step of a design: settle pattern + data/access model + boundaries before drilling into framework mechanics." NOT_FOR - "Framework-specific module/schema/job/authorization mechanics — that belongs to a stack-specific architecture skill." - "Writing or verifying implementation code — this skill informs design decisions, it does not produce code."
Core knowledge (the map)
KNOWLEDGE METHOD - "PLAN before mechanics: a design starts by choosing a PATTERN, settling the DATA + ACCESS model, and naming the BOUNDARIES — then drills into technology-specific implementation." - "Every pattern and technology choice is a TRADE-OFF, not a default. Start simple (a monolith / modular monolith) and adopt complexity (microservices, CQRS, event sourcing) only when a concrete force — scale, team autonomy, independent deploy, audit/replay — demands it." - "Right-size the decision to the requirements you actually have: estimate scale FIRST (capacity-planning workflow), then let the numbers drive the pattern and the technology choices." - "Make decisions with a framework, not a hunch: each technology choice in tech_decision_guide.md carries a decision matrix + a 'when to use each' so the choice is defensible."
What ships with it
4 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.
- 1mo ago First seen · 71 lines · 204 tokens per session scan A bbb3332e7ffc
system-architecture is a skill published in the GitHub repository endorphin-ai/hasbrains-agent-kit (9 stars, last pushed 12d ago), licensed MIT. It adds 204 tokens to every session and 1,088 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
hydra
Multi-agent orchestration framework for Claude Code. Automatically delegates tasks to cheaper, faster sub-agents (Haiku, Sonnet) while maintaining Opus-level quality through verification. Use when working on any coding task — Hydra activates automatically to route file exploration, test running, documentation, code…
rfc
Manage architecture RFCs: create, review, list, update, and transition status. Use when user mentions "RFC", "technical proposal", "architecture proposal", or wants to draft, review, list, update, or change status of RFCs.
cleaning-up-branches
Deletes merged git branches (local and remote) and flags stale unmerged branches for manual review. Use when user mentions "cleanup branches", "delete merged branches", "prune old branches", "remove stale branches", "branch cleanup", or runs /cleanup-branches command.
prototype
Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery. Use when user runs /prototype, asks to "prototype a UI", "mock up a component", "generate HTML mockups", "create UI variations", "design exploration", "quick UI concept", or wants to…
quality-stack
Scan a project to detect configured quality and testing tools across JVM (Gradle/Maven), Android (AGP/Compose/KMP), Node.js/TypeScript, and Python ecosystems. Cross-reference against research-backed recommendations and assist with setup. Auto-detects project type(s) including monorepos with mixed ecosystems. Use when…
doc-freshness
Detect documentation drift, stale references, and cross-document inconsistencies in any project. Scans for code-doc drift (API/function changes not reflected in docs), cross-doc drift (conflicting information across documents), and stale references (broken links, deleted files, outdated versions). Use when checking…