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/verygoodplugins/claude-pluginsWrote 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/verygoodplugins/claude-plugins/research-save)<a href="https://agentmods.dev/commands/verygoodplugins/claude-plugins/research-save"><img src="https://agentmods.dev/badge/commands/verygoodplugins/claude-plugins/research-save/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/verygoodplugins/claude-plugins/research-save"><img src="https://agentmods.dev/badge/commands/verygoodplugins/claude-plugins/research-save.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 | $0.00006 | $0.00302 |
| Opus 5.5 | $0.00002 | $0.00121 |
| Sonnet 5.5 | $0.00001 | $0.00060 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
research-save 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 1mo 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
Save Research
Save research findings, web content, or project notes to Evernote with automatic organization.
Usage
/research-save [topic]
Workflow
-
Determine content to save:
- Research summary from current session
- Web content being discussed
- Code snippets or technical findings
- Meeting notes or decisions
-
Find or create appropriate notebook:
mcp__evernote__evernote_list_notebooks({}) -
Format the content:
- Add clear title with date/topic
- Structure with headings
- Include source links
- Add relevant code blocks
-
Create the note:
mcp__evernote__evernote_create_note({ title: "[Topic] - Research Notes - YYYY-MM-DD", content: "## Summary\n\n[Key findings]\n\n## Details\n\n[Detailed notes]\n\n## Sources\n\n- [links]", notebookGuid: "<research-notebook-guid>", tags: ["research", "topic-tag", "YYYY-MM"] })
Best Practices
- Use consistent title format for easy searching
- Tag with both topic and date (YYYY-MM)
- Include source links for reference
- Structure content with clear headings
- Add a summary at the top for quick scanning
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.
- 1mo ago First seen · 53 lines · 6 tokens per session scan A 5ec92f4ad904
research-save is a command published in the GitHub repository verygoodplugins/claude-plugins (2 stars, last pushed 8mo ago), licensed MIT. It adds 6 tokens to every session and 302 once invoked, about $0.0000 per session on Opus 5.5. 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
gws-people
Search and look up Google Contacts and directory profiles.
gws-chat
Send messages and manage Google Chat spaces.
gws-keep
List and read Google Keep notes.
meeting-prep
Prepare for your next meeting with agenda and attendees.
standup
Generate a standup report from Google Workspace data.
agenda
Show upcoming calendar events.