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/kumaran-is/claude-code-onboarding/asidegit clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/kumaran-is/claude-code-onboarding/aside)<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/aside"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/aside.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00557 |
| Opus 5 | $0.00000 | $0.00279 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
aside 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 today.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aside — Answer a Side Question Without Losing Task State
Freeze current task state, answer the side question, then resume exactly where you left off.
Behavior
When /aside is invoked (or the user says "aside:" or "quick question:"):
- FREEZE — note the current task and last completed step
- READ-ONLY mode — do not write code, create files, or run destructive commands during the aside
- ANSWER — respond to the side question fully
- RESUME — end the response with the footer below
Resume Footer (mandatory)
Every aside response MUST end with:
---
**— Back to task:** [task name] — next step: [specific next action]
Example
User is in the middle of implementing a NestJS auth guard when they ask:
aside: what's the difference between JWT and session auth?
Response structure:
[Full answer to the JWT vs session question]
---
**— Back to task:** NestJS JWT auth guard — next step: implement `canActivate()` method in `auth.guard.ts`
Edge Cases
No question provided
/aside
Response: "What's the side question? (Currently working on: [task])"
Question reveals a problem with current task
If the side question reveals that the current approach is wrong:
[Answer the question]
⚠️ This affects the current task: [explain impact]
Options:
A) Continue current approach with this caveat in mind
B) Stop and revise the approach before continuing
→ Which do you prefer?
---
**— Back to task:** [task name] — awaiting direction on approach
Question is actually a task redirect
If the "aside" is really a new task (e.g., "aside: actually, implement X instead"):
This sounds like a task change, not a side question.
Current task: [task name] (last completed: [step])
Options:
A) Abandon current task and start [new task]
B) Finish current task first, then do [new task]
C) Keep this as a genuine aside — just explain [concept], don't implement
→ Which do you prefer?
Constraints
- Do NOT write files, run builds, or modify state during an aside
- Do NOT lose track of the current task — always end with the resume footer
- The aside answer must be complete — do not defer it to "after the task"
- If the aside answer would take more than ~5 tool calls, flag it: "This aside is large — should we pause the task formally?"
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.
- today First seen · 81 lines · 0 tokens per session scan A ffb79439f757
aside is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 557 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.