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/drag88/claude-dev-framework/researchgit clone --depth 1 https://github.com/drag88/claude-dev-frameworkWhat 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 | $0.00009 | $0.00373 |
| Opus 5 | $0.00005 | $0.00187 |
| Sonnet 5 | $0.00002 | $0.00075 |
| Haiku 4.5 | $0.00001 | $0.00037 |
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 yesterday.
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
/cdf:research - Deep Research Command
Triggers
- Research questions beyond knowledge cutoff
- Complex research questions
- Current events and real-time information
- Academic or technical research requirements
- Market analysis and competitive intelligence
Context Trigger Pattern
/cdf:research "[query]" [--depth quick|standard|deep|exhaustive] [--strategy planning|intent|unified]
Behavioral Flow
Scope the question, decide how many hops of research it needs, search in parallel batches, and synthesize with sources cited — deeper or more ambiguous questions warrant more hops.
Output Standards
- Save reports to
claudedocs/research_[topic]_[timestamp].md - Include executive summary
- Provide confidence levels
- List all sources with citations
Examples
/cdf:research "latest developments in quantum computing 2024"
/cdf:research "competitive analysis of AI coding assistants" --depth deep
/cdf:research "best practices for distributed systems" --strategy unified
Boundaries
Will: Current information, intelligent search, evidence-based analysis Won't: Make claims without sources, skip validation, access restricted content
Agent Routing
| Research Context | Primary Agent | When to Use |
|---|---|---|
| Technical topics | deep-research-agent | Architecture patterns, algorithms, best practices |
| Market/business | business-research-strategist | Market sizing, competitive analysis, business models |
| Library selection | library-researcher | Package comparison, maintenance health, migration risk |
Next Commands
/cdf:design— Design systems based on research findings/cdf:brainstorm— Explore requirements informed by research
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.
- yesterday First seen · 50 lines · 9 tokens per session scan A 1b89e7fc6130
research is a command published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 373 once invoked, about $0.0000 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.