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/brettbuddin/claude-plugins/researchgit clone --depth 1 https://github.com/brettbuddin/claude-pluginsWhat 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 | $0.00032 | $0.00445 |
| Opus 5 | $0.00016 | $0.00222 |
| Sonnet 5 | $0.00006 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00044 |
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 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
Research
Dispatch the Researcher agent to produce a research report, then run git history analysis on the key paths it identified.
Args
<topic/area description> (required). If no description is provided, reply with a short usage summary and stop.
Steps
Configuration
- Use the
smith:configskill to read project configuration. Use theoutput_directoryvalue (default:docs/) wherever<output_directory>appears below.
Phase 1: Research
- Use the Task tool with
subagent_type: "Researcher"andrun_in_background: false. - Prompt the agent with the topic/area description provided by the user.
- After completion, note the research file path (e.g.,
<output_directory>/research/TOPIC.md).
Phase 2: History
Skip this phase if the research_history configuration option is false.
- Read the research file produced in Phase 1. Extract the key file and directory paths from the Key Components and Architecture sections.
- Use the Task tool with
subagent_type: "Historian"andrun_in_background: false. - Prompt the agent with:
- The absolute path to the research file.
- The list of key paths extracted in step 4.
Wrap-Up
- Tell the user the research file path and suggest they review it, annotate it if needed and run
/revise-research, or proceed to/plan <goal>.
Prompting the Agents
When constructing the prompt for the Task tool, include:
- The user's description (Phase 1) or key paths (Phase 2)
- The working directory path so the agent knows where to find/write files
- Any additional context the user provided in the conversation
Do NOT paste the agent's own instructions into the prompt; the agent definitions are already loaded by the Task tool via subagent_type.
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 · 50 lines · 32 tokens per session scan A 26a084f17068
research is a command published in the GitHub repository brettbuddin/claude-plugins (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 445 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
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.