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/basher83/agent-auditor/parallel-researchgit clone --depth 1 https://github.com/basher83/agent-auditorWhat 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 | $0.00467 |
| Opus 5 | $0.00005 | $0.00234 |
| Sonnet 5 | $0.00002 | $0.00093 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
parallel-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 2d 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.
What it actually says
Parallel Research Command
Research multiple topics simultaneously by spawning parallel jina-search sub-agents.
Arguments
Topics to research: $ARGUMENTS
Process
Follow these steps to execute parallel research:
Step 1: Parse Topics
Split the arguments into individual research topics. Each distinct argument represents one research topic.
Step 2: Create Sub-Agent Prompts
For each topic, prepare a research prompt:
Research [topic] and create a comprehensive report.
Focus on:
- Current best practices
- Latest developments and documentation
- Practical implementation guidance
- Authoritative sources
Save findings to docs/research/[topic-slug].md
Step 3: Launch Parallel Sub-Agents
CRITICAL: Launch ALL sub-agents in a SINGLE message with multiple Task tool calls.
For each topic, create a Task tool call:
subagent_type: "jina-search"description: "Research [topic]"prompt: The research prompt from Step 2
Step 4: Report Results
After all sub-agents complete, provide a summary:
## Parallel Research Complete
**Topics Researched**: [COUNT]
**Reports Generated**:
- docs/research/[topic1-slug].md
- docs/research/[topic2-slug].md
- docs/research/[topic3-slug].md
**Next Steps**:
- Review reports for consistency
- Cross-reference findings across topics
- Synthesize key insights
Examples
Single topic:
/parallel-research "React performance optimization"
Multiple topics:
/parallel-research "React Hooks" "Vue Composition API" "Svelte stores"
Complex topics with spaces:
/parallel-research "Next.js 14 server components" "Remix data loading patterns" "Astro content collections"
Output
Each sub-agent will create an independent research report in docs/research/ with comprehensive findings, citations, and actionable recommendations.
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.
- 2d ago First seen · 88 lines · 0 tokens per session scan A 0840b7cd2efd
parallel-research is a command published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 467 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 2026-08-31.
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.