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/d-mariano/spicyclaude/exploregit clone --depth 1 https://github.com/d-mariano/spicyclaudeWrote 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/d-mariano/spicyclaude/explore)<a href="https://agentmods.dev/commands/d-mariano/spicyclaude/explore"><img src="https://agentmods.dev/badge/commands/d-mariano/spicyclaude/explore.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 5.1 | $0.00048 | $0.00657 |
| Opus 5 | $0.00024 | $0.00329 |
| Sonnet 5 | $0.00010 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
explore 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 5d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Do not write any code right now. We are going to discuss working on $ARGUMENTS.
If you are given an identifier, attempt to use configured MCP servers like Jira to search for the related resource. If you are given a PRD, read it.
You are going to read through related code and conduct any web searches.
Perform a deep dive, gather enough context to become a subject matter expert.
Considerations
- Conduct web searches on frameworks, protocols, APIs, or standards in use — unless usage examples in code are telling enough
- Research if third-party packages in use already provide required types and explicitly call this out
Surfacing Open Questions
When you hit a meaningful fork you cannot resolve from inputs — ambiguous scope, two equally-promising directions to dig into, contradictory sources — raise it via AskUserQuestion instead of silently picking. Do NOT use AskUserQuestion for low-stakes choices the model can reasonably commit to and document. Explore is no-output, so these questions are purely conversational steering.
Rules:
- Batch related questions — up to 4 per call.
- Provide 2-4 options per question. Each option needs a one-line description.
- Every option's description includes a counter. Format:
"<implication> · Counter: <trade-off or objection>". If an option has no real counter, the option set needs rework. - Mark your recommendation with "(Recommended)" only when you have a clear, evidence-backed lean from inputs — not absence of contrary signal. The recommended option gets the strongest counter — the primary reason the user might reject it. Place the recommended option first in the options array.
headeris hard-capped at 12 characters. Pick a short tag ("Scope", "Direction", "Subsystem"); don't write a sentence.- State why the question matters in the question text — which goal, constraint, or downstream decision rides on the answer.
- Always offer a defer path unless exploration genuinely cannot proceed. Phrase:
"Defer — note in conversation, proceed both directions". Deferred forks have no doc to land in; carry them in conversational context only. - Options come from inputs only. Don't draw on training-data preferences when proposing option sets. If inputs don't suggest any, that's an unknown — flag it, don't invent options.
- Use
multiSelect: truewhen the choices are not mutually exclusive — e.g., "Which subsystems should I scope into the discussion?", "Which angles do you want covered?". Defaultfalsefor picking-one decisions. - Do NOT add an "Other" option. The tool surfaces a free-text input automatically; adding "Other" wastes one of the 4 option slots.
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.
- 5d ago First seen · 35 lines · 48 tokens per session scan A c7ad3ecd9ba9
explore is a command published in the GitHub repository d-mariano/spicyclaude (5 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 657 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 2026-08-31.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.