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 skills add jezweb/vite-flare-starter --skill save-research-docgit clone --depth 1 https://github.com/jezweb/vite-flare-starterWrote 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/skills/jezweb/vite-flare-starter/save-research-doc)<a href="https://agentmods.dev/skills/jezweb/vite-flare-starter/save-research-doc"><img src="https://agentmods.dev/badge/skills/jezweb/vite-flare-starter/save-research-doc/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/skills/jezweb/vite-flare-starter/save-research-doc"><img src="https://agentmods.dev/badge/skills/jezweb/vite-flare-starter/save-research-doc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 54 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00049 | $0.00534 |
| Opus 5 | $0.00024 | $0.00267 |
| Sonnet 5 | $0.00010 | $0.00107 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
save-research-doc 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 10d 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 Document
When to use
- "Save this for me"
- "File this under [topic]"
- "I want to keep this research"
- After producing a substantial result the user wants to retain
Steps
-
Identify what to save — usually it's the most recent assistant output. If ambiguous, confirm via
ask_questions. -
Decide on path and filename:
- Top-level folder by topic:
research/,notes/,briefs/,code/,drafts/ - Filename with date for time-sensitive content:
YYYY-MM-DD-slug.md - Otherwise descriptive slug:
analyse-pricing-strategy.md - All lowercase, hyphens not spaces
- Top-level folder by topic:
-
Add frontmatter — the document gets YAML frontmatter for searchability:
--- title: [Document title] created: [ISO date] tags: [tag1, tag2] summary: [One-sentence summary] sources: [optional list of URLs cited] --- -
Format the body:
- H1 title at the top
- Source content cleaned up (preserve markdown formatting)
- Inline source links if research-based
- Footer with "Last updated: [date]"
-
Write the file — call
fs_writewith the path and content. -
Confirm and offer follow-ups:
- Show the path and size via plain message
- Use
offer_choices: "Open the file", "Save another version", "Add to a topic index", "Done"
Style
- Generous structure. Use headings, bullet points, dividers — make it scannable later.
- Always add the date — future you needs to know when this was true
- Cross-link related saved docs if you know about them (call
fs_listto check)
What not to do
- Don't save without permission if the conversation didn't explicitly ask
- Don't overwrite without warning. Check
fs_readfirst; if exists, ask viaconfirm_action - Don't save sensitive data (passwords, keys, personal info that shouldn't be persisted)
- Don't dump raw chat transcript — synthesise the useful content
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.
- 10d ago First seen · 57 lines · 49 tokens per session scan A 3eac47f45283
save-research-doc is a skill published in the GitHub repository jezweb/vite-flare-starter (48 stars, last pushed 15d ago), licensed MIT. It adds 49 tokens to every session and 534 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.