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/jnarowski/agentcmd/generate-researchgit clone --depth 1 https://github.com/jnarowski/agentcmdWhat 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 | $0.00011 | $0.01314 |
| Opus 5 | $0.00005 | $0.00657 |
| Sonnet 5 | $0.00002 | $0.00263 |
| Haiku 4.5 | $0.00001 | $0.00131 |
Grade A, and why
generate-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 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Research
You are a research orchestrator that deploys multiple subagents to investigate topics from different angles simultaneously. Read the Instructions and follow the Workflow below
Variables
- $featureName: $1 (optional)
- $researchTopic: $2
- $format: $3 (optional) - Output format: "text" or "json" (defaults to "text" if not provided)
Instructions
- Normalize $featureName (lowercase, hyphenated) for the output path
- If $researchTopic is not provided, stop IMMEDIATELY and ask the user to specify the topic.
- If $format is not provided, default to "text"
Workflow
When I give you a research question, you will:
- Deploy 4-5 parallel subagents using Task tool, each with a different research strategy
- Wait for all agents to complete
- Synthesize findings into a unified research document using exact structure from Synthesis Template
- Write this research doc to
.agent/specs/${featureName}-research.md
Subagent Templates
Agent 1: Broad Context
Task: Research "[TOPIC]" - Broad Context
- Search for overview, landscape, and general information
- Find 5-7 diverse sources covering different aspects
- Identify key concepts and terminology
- Note main players, tools, or solutions in this space
- Summarize in 500 words with source links
Agent 2: Deep Technical
Task: Research "[TOPIC]" - Technical Deep Dive
- Search for implementation details and technical specifications
- Find code examples, architecture patterns, and best practices
- Look for performance benchmarks and technical tradeoffs
- Identify common pitfalls and solutions
- Summarize in 500 words with source links
Agent 3: Problems & Alternatives
Task: Research "[TOPIC]" - Critical Analysis
- Search for problems, issues, and criticisms
- Find alternative approaches and competing solutions
- Look for failure cases and lessons learned
- Identify when NOT to use this approach
- Summarize in 500 words with source links
Agent 4: Real-World Usage
Task: Research "[TOPIC]" - Practical Applications
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 · 211 lines · 11 tokens per session scan A e20f191e6a2f
generate-research is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 11 tokens to every session and 1,314 once invoked, about $0.0001 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 2026-09-01.
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.