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 badrabbitt/leanrigor --skill senior-system-designgit clone --depth 1 https://github.com/badrabbitt/leanrigorWrote 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/badrabbitt/leanrigor/senior-system-design)<a href="https://agentmods.dev/skills/badrabbitt/leanrigor/senior-system-design"><img src="https://agentmods.dev/badge/skills/badrabbitt/leanrigor/senior-system-design/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/badrabbitt/leanrigor/senior-system-design"><img src="https://agentmods.dev/badge/skills/badrabbitt/leanrigor/senior-system-design.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 | $0.00062 | $0.00727 |
| Opus 5.5 | $0.00025 | $0.00291 |
| Sonnet 5.5 | $0.00012 | $0.00145 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
senior-system-design 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior system design
A design is a set of decisions with stated consequences. Prose that describes components without deciding anything is not a design.
Write the design to architecture.md, one section per heading below. Each
section must end in a decision or an explicitly recorded unknown.
references/nfr-checklist.md holds the detailed prompts; consult it when a
section feels thin.
1. Functional requirements
What the system must do, as capabilities a caller can invoke. Number them so the rest of the document can refer to them.
2. Non-functional requirements
State numbers, not adjectives. Required: request rate, data volume, latency target and the percentile it applies to, availability target, durability expectation, consistency model, retention. "Fast" and "reliable" are not requirements.
3. Capacity assumptions
Show the arithmetic: requests per second, bytes per record, records per day, storage at one year, peak-to-average ratio. Label every input as measured, estimated or assumed. A capacity section with no arithmetic is a guess wearing a suit.
4. Data
Entities, ownership, access patterns, indexes implied by those patterns, and the migration path from what exists today. Say which component owns each write.
5. Failure modes
For each dependency: what happens when it is slow, when it is down, and when it returns wrong data. Then decide, per call: timeout, retry policy with backoff and jitter, retry budget, idempotency, and what the caller sees when you give up. Retries without a budget turn one failure into an outage.
6. Security boundaries
Where trust changes hands. For each boundary: what authenticates the caller, what authorizes the action, what is validated, what is logged, and what must never be logged. Name where secrets live and how they rotate.
7. Observability
The signals that would let someone diagnose this at 3am: the SLI and its target, the alert that fires when users are affected — not when a machine is busy — the dashboard, and the trace or log field that ties a user report to a request.
What ships with it
3 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 Changed · +67 lines · +33 tokens per session e65dd4e9ca8e
- 2mo ago First seen · 8 lines · 29 tokens per session scan A 8dc542e127e5
senior-system-design is a skill published in the GitHub repository badrabbitt/leanrigor (0 stars, last pushed 22d ago), licensed Apache-2.0. It adds 62 tokens to every session and 727 once invoked, about $0.0002 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
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
context-engineering
A guide to organizing the instructions and information an AI agent receives at each step. It covers system prompts, tool descriptions, conversation history, on-demand skills, and protections against unsafe outside content.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
multi-agent-design
A guide to deciding when several AI agents should work together and how they should share tasks, context, and files. It compares peer, manager-led, and decentralised arrangements and explains common coordination failures.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
loop-engineering
A guide to building reliable loops for AI agents that plan, act, check their work, and continue until a task is truly complete. It includes independent verification and a proposer-reviewer pattern in which one agent's work is checked using outside evidence.