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/explorationgit 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/exploration)<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/exploration"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/exploration.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 | $0.00047 | $0.01168 |
| Opus 5 | $0.00023 | $0.00584 |
| Sonnet 5 | $0.00009 | $0.00234 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
exploration 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/exploration — CTO Challenge Mode
Purpose
Before writing a single line of code, play devil's advocate against the proposed solution. This is NOT brainstorming (divergent). This is adversarial convergence — stress-testing a specific plan before committing to it.
Core philosophy: "5 minutes of questioning before coding beats 5 hours of fixing after."
Difference from /brainstorm:
/brainstorm→ divergent: generates ≥3 options when direction is unclear/exploration→ convergent: challenges a specific proposed solution when direction is set
When to Use
- About to implement a new feature or architectural change
- You have a specific approach in mind and want it challenged
- You feel "ready to start coding" but something feels uncertain
- The task touches >2 services, a schema change, or a new dependency
NOT when to use
- Direction is genuinely unclear (use
/brainstorminstead) - Task is a trivial bug fix or <50 line change
- Implementation is already approved and underway
Execution Steps
Step 1: Understand the Proposed Solution
Ask the user to describe in 2-3 sentences:
- What they want to build
- The specific approach they have in mind
Step 2: CTO Challenge Mode — 5 Adversarial Questions
From a tech lead perspective, ask ALL 5 before evaluating:
-
Why this approach instead of [alternative]?
- For our stack: Is this the right layer (NestJS vs Spring vs FastAPI)?
- Could a Firebase/Cloud Run managed service replace self-hosting this?
- Is there an existing skill/pattern in
.claude/skills/that already solves this?
-
What are the boundary conditions?
- What happens at 0 records? At 1M records?
- What happens if the external service (Firebase/Stripe/etc.) is down?
- What's the behavior on concurrent writes (R2DBC/Prisma transactions)?
-
What happens in the worst case?
- If this fails in production, what data is at risk?
- Is there a rollback path? (Required by
first-principles.mdLayer 3) - Does failure fail loudly or silently? (code-standards.md: No Silent Failures)
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 · 124 lines · 47 tokens per session scan A 7b3640b005e6
exploration is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,168 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 2026-09-03.
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.