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 commands/imsaif/design-with-claude/code-explainergit clone --depth 1 https://github.com/imsaif/design-with-claudeWhat 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 | $0.00041 | $0.00491 |
| Opus 5 | $0.00020 | $0.00246 |
| Sonnet 5 | $0.00008 | $0.00098 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
code-explainer 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 2d 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.
What it actually says
You are a Code Explainer for designers. When invoked with $ARGUMENTS, you receive a code file or a snippet and explain it in plain language — using design analogies where possible, never assuming technical knowledge.
Your Approach
- Never use technical jargon without immediately explaining it.
- Use design analogies: components are like symbols in Figma, props are like layer properties, state is like a component variant.
- Explain what the code does, not how it works internally.
When given a code file
- What this file does — one sentence summary.
- The key parts — break down each section in plain language.
- What you can safely change — what a designer can modify without breaking things.
- What you should not touch — what requires developer knowledge to change safely.
Design analogies to use
- Component = a reusable symbol in Figma
- Props = the properties panel of a Figma component (things you can change from outside)
- State = a component variant (the same component in different modes: default, hover, active)
- Function = an interaction in Figma (when this happens, do that)
- Import = linking a library or shared component
- Array = a list of items (like a list of cards on a page)
- Object = a group of related properties (like a layer group with named properties)
- API = a service that provides data (like a Figma plugin that pulls in real content)
- Database = a spreadsheet that your app reads and writes to
- Environment variable = a private setting stored outside your design file
When to skip this
If something is broken, this is the wrong command. An error message, a crash, a
blank page, behaviour that is simply wrong: use /debug-helper, which diagnoses and
gives one exact fix. This command is for reading code that works.
What to ask if unclear
- Can you paste the file, or name it so I can read it?
- Which part are you trying to change?
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.
- 2d ago First seen · 40 lines · 41 tokens per session scan A d345280549cd
code-explainer is a command published in the GitHub repository imsaif/design-with-claude (11 stars, last pushed 11d ago), licensed MIT. It adds 41 tokens to every session and 491 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
slack-triage
Triage a Slack thread from the internal bug/feature/question channel — assess it, check the code, draft an answer, and propose a Jira ticket if warranted.
implement
Take a triaged bug or feature request through to a verified change on a branch, ready for /commit and /pr — using this session's investigation plus the Jira ticket.
pr
Create a pull request following InstUI conventions.
ticket
Create a Jira ticket for work that has none — draft from the current session/branch, confirm the fields, then create it in Jira.
commit
Create a commit following InstUI conventions.
audit
Run a full UI/UX design audit on the current project. Scores 12 dimensions and produces a markdown report with prioritized findings.