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 causify-ai/helpers --skill research_idea.add_from_filegit clone --depth 1 https://github.com/causify-ai/helpersWrote 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/causify-ai/helpers/research_idea.add_from_file)<a href="https://agentmods.dev/skills/causify-ai/helpers/research_idea.add_from_file"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/research_idea.add_from_file/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/causify-ai/helpers/research_idea.add_from_file"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/research_idea.add_from_file.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 3 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00013 | $0.00946 |
| Opus 5.5 | $0.00005 | $0.00378 |
| Sonnet 5.5 | $0.00003 | $0.00189 |
| Haiku 4.5 | $0.00001 | $0.00095 |
Grade A, and why
research_idea.add_from_file 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Given a file
<FILE>containing research ideas in a very early, unstructured form (loose fragments, one-liners, mixed bullets), add a## <Title>header above each distinct idea, then, once the user approves, create one template-formatted research idea file per idea
Workflow
Read the Inputs
- Read
<FILE> - Read the template
.claude/templates/research_idea.template.md - Read
.claude/skills/research_idea.rules.mdfor file naming and directory conventions - Read the file names under
research/ideas/*.mdto know which ideas already exist
Title and Group the Fragments
- Split
<FILE>into distinct ideas- Merge fragments that clearly describe the same idea into one group; it is fine to reorder or combine fragments that belong together
- Keep fragments that are already distinct ideas separate, even if short
- Add a
## <Title>header directly above each idea's raw content<Title>is a short noun phrase (3-8 words) that names the idea, in the same style as existing file names, e.g.Hierarchical Training,Compression as Proxy for Understanding- If a fragment already has a
##header, keep or refine that title instead of adding a duplicate one
- Do not summarize, expand, or fabricate content; only add headers and move fragments next to the other fragments of the same idea
- Flag (do not silently drop) any fragment whose idea already exists as a file
under
research/ideas/*.md, so the user can decide whether to skip it - Write the titled, grouped result back into
<FILE>
Wait for the User
- Show the user the list of proposed titles and which fragments were grouped under each
- Wait for the user to review and approve
<FILE>before creating any new idea file - If the user requests different titles or groupings, apply the changes and present the file again
Create One Idea File per Approved Idea
- For each approved
## <Title>section, createresearch/ideas/draft.<Idea_Name>.md, per.claude/skills/research_idea.rules.md## Status Prefixes<Idea_Name>is<Title>in Title_Case_With_Underscores, matching existing file names (e.g.Hierarchical Training->Hierarchical_Training)
- Seed the new file with the section's raw content as the seed for
Core Idea - Skip creating a file for any idea the user chose to skip in Step 3
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 Changed · +1 lines 088e09c51a4b
- 1mo ago First seen · 86 lines · 13 tokens per session scan A 2b894e3d5707
research_idea.add_from_file is a skill published in the GitHub repository causify-ai/helpers (150 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 946 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…