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.
git 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/research)<a href="https://agentmods.dev/commands/d-mariano/spicyclaude/research"><img src="https://agentmods.dev/badge/commands/d-mariano/spicyclaude/research/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/commands/d-mariano/spicyclaude/research"><img src="https://agentmods.dev/badge/commands/d-mariano/spicyclaude/research.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 | $0.00044 | $0.01118 |
| Opus 5 | $0.00022 | $0.00559 |
| Sonnet 5 | $0.00009 | $0.00224 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
research 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 8d 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 — 69 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
- Always share usage examples and best practices when found
- Research if third-party packages in use already provide required types and explicitly call this out
- If alternative approaches are identified and you have identified a preference, only mention your preference
- Favour simplicity and elegance
- Always cite your sources
Surfacing Open Questions
Research is the front-loaded chance to resolve ambiguity while the user is still context-loaded on the PRD. Every PRD/AC ambiguity that survives this phase becomes a planning-time interrupt later — by which point the user has moved on and has to re-context-load to answer. Push hard upstream.
Mandatory pre-output question pass
Before writing the research doc, do a dedicated sweep for unresolved upstream ambiguity and surface every fork via AskUserQuestion (batched, up to 4 per call; chain calls if more remain). Trigger on:
- PRD/AC ambiguity — any AC clause open to two reasonable interpretations; any goal whose success metric is undefined; any persona/use-case the PRD names but doesn't bound.
- Scope boundary — anything plausibly in or out where the PRD doesn't decide; non-goals that the natural design path would still touch.
- Contradictory sources — PRD vs. cited research; two cited sources that disagree on a load-bearing fact.
- Approach forks where the answer changes the recommended direction — two equally-promising libraries/protocols/patterns where the choice gates which deep-dive is worth doing.
- Cross-cutting prerequisites — auth, tenancy, data residency, compliance constraints the PRD assumes but doesn't pin down.
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.
- 8d ago First seen · 69 lines · 44 tokens per session scan A db4b5efcf245
research is a command published in the GitHub repository d-mariano/spicyclaude (5 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,118 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.