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 atman-33/workhub --skill system-designgit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/system-design)<a href="https://agentmods.dev/skills/atman-33/workhub/system-design"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/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/atman-33/workhub/system-design"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/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 | $0.00102 | $0.01496 |
| Opus 5.5 | $0.00041 | $0.00598 |
| Sonnet 5.5 | $0.00020 | $0.00299 |
| Haiku 4.5 | $0.00010 | $0.00150 |
Grade A, and why
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 17d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System design
Turn a request into a settled design and a set of design documents a human can review and an agent can implement from. Two phases, in order: settle the design with the user, then write it down. Writing is not a substitute for asking — a document built on guesses reads as settled and is not.
Planning boundary. This skill produces documents only. Do not edit application code, even if the request says "build it". After the documents are written, stop and wait for a new request to implement.
Outputs
All files go flat into the output folder — no subfolders, so the set also fits a workhub backlog item folder:
| File | Holds | Template |
|---|---|---|
proposal.md |
Why, what changes, capabilities, impact | templates/proposal.md |
spec-<capability>.md |
One per capability: requirements with WHEN/THEN scenarios | templates/spec.md |
design.md |
How: context, goals/non-goals, decisions with alternatives, risks, open questions | templates/design.md |
uml.md |
Diagrams in Mermaid: use case, ER, sequence, file change map | templates/uml.md |
There is deliberately no task list: breaking the work into tasks belongs to whatever runs the implementation (a task board, a TDD loop), and a second copy here would drift.
Steps
1. Take in the request
The user supplies the requirement or feature description, often with links, notes or screenshots. Read everything they point at.
Then gather the facts yourself: read the relevant code, configuration,
existing docs and data models of the target repository. Delegate a broad sweep
to a sub-agent (the built-in Explore agent) rather than reading dozens of
files here. Never ask the user for something you can look up.
2. Decide the output folder
Use the folder the user named. If they named none, ask — with a recommended answer, not an open question:
- running inside a workhub task whose
backlog:item is known → recommend that item's folder (projects/NNNN-<slug>/backlog/B-NNN-<slug>/); - otherwise → recommend
docs/design/<change-name>/in the target repository, where<change-name>is a kebab-case name derived from the request.
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.
- 17d ago Changed 4d3b08460d85
- 27d ago First seen · 143 lines · 102 tokens per session scan A ec96cee55407
system-design is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 1,496 once invoked, about $0.0004 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 2026-09-20.
Other skills, from other repositories
gonavi-cli
Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
trellis-break-loop
Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs.
trellis-channel
Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.
readmd-skill-creator
Use when a ReadMD user wants to design, test, or improve a reusable document-writing Skill.
trellis-start
Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/. Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow. Use when beginning a new coding session, resuming work, starting a new task, or…