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.
git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standardWrote 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/commands/hoangnguyen0403/agent-skills-standard/system-design-session)<a href="https://agentmods.dev/commands/hoangnguyen0403/agent-skills-standard/system-design-session"><img src="https://agentmods.dev/badge/commands/hoangnguyen0403/agent-skills-standard/system-design-session/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/commands/hoangnguyen0403/agent-skills-standard/system-design-session"><img src="https://agentmods.dev/badge/commands/hoangnguyen0403/agent-skills-standard/system-design-session.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 | $0.00000 | $0.01060 |
| Opus 5 | $0.00000 | $0.00530 |
| Sonnet 5 | $0.00000 | $0.00212 |
| Haiku 4.5 | $0.00000 | $0.00106 |
Grade A, and why
system-design-session 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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Design Session
Run an interactive system design session that turns a product goal into a sized, justified architecture with diagrams, ADRs, a scorecard, and a machine-readable handoff.
Input: $ARGUMENTS
Optional args: slug=, ticket=<id/url>, mode=interactive|autonomous|channel, channel=, auto_continue=true|false, profile=business|hybrid|technical.
Instructions
Execute the following steps for $ARGUMENTS.
System Design Workflow (Architecture / How Big)
Goal: Produce a capacity-justified architecture baseline that design-solution can turn into contracts.
Steps
- Load inputs:
- Load
system-design-methodologyplus matched siblings (estimation, building-blocks, data-architecture, resilience-ops, review, principles, diagramming). - Load PRD or ticket, existing architecture docs, and current traffic/incident data when reviewing an existing system.
- Load
- Classify and announce:
- Mode: new design | review existing | interview practice.
- Depth: quick sketch (defaults assumed, each labeled
ASSUMED) or full session (every gate confirmed). - Escalate quick to full when an irreversible or cross-team choice appears.
- Intake (gate):
- Ask max 3 blocking questions per turn from the intake checklist; supply a recommended default for each.
- Record functional requirements, NFR targets, out-of-scope fence, operating team, and every
ASSUMEDvalue. - Review-existing mode: map current state, measure real traffic and incidents, and name the binding constraint before proposing change.
- Estimate (gate):
- Compute average and peak QPS, storage over retention, bandwidth, working-set memory, and monthly cost at that scale.
- Name the shaping quantity and confirm the order of magnitude before any component is drawn.
- Design incrementally:
- Price the null option first (do nothing, buy, or extend an existing service); rejecting it needs a stated reason.
- Start from client, API, service, store; add one component at a time as
constraint -> component -> cost. - Fix API surface, data ownership, and consistency class per flow.
- Render diagrams only after the component set is agreed, per
system-design-diagramming: anarchitectureview plussequenceordataflowfor the critical path.
- Deep dive and decide:
- Dispatch the 2-3 riskiest components to
specialist-system-architect, one brief each with its numbers and consistency requirement. - Merge the returned options, failure modes, and irreversible decisions; state bottlenecks, SPOFs, and rejected alternatives with reasons.
- Write one ADR per irreversible decision, each with its reversal trigger; stage the plan as build now, enabling seam, and the metric threshold that triggers the next step.
- Save the design to
docs/design/system-design-[slug].mdwhen file writes are allowed.
- Dispatch the 2-3 riskiest components to
- Score and hand off:
- Run the nine-axis scorecard (including cost proportionality), record the risk register, and emit the handoff payload.
- Route to
design-solution; return toplan-featurewhen product scope is still undefined.
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.
- 9d ago First seen · 92 lines · 0 tokens per session scan A 64385593bb10
system-design-session is a command published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,060 tokens. 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 2026-09-03.
Other commands, from other repositories
api-design
A command for guiding API design work through the Universal Development Standards workflow.
harden
Add loading/error/empty states, mounted guards, disposal, null safety tightening. Makes screens production-ready.
explain
Explain how the following works in this NestJS codebase: $ARGUMENTS.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.