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 hec-ovi/research-skill --skill researchgit clone --depth 1 https://github.com/hec-ovi/research-skillWrote 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/hec-ovi/research-skill/research)<a href="https://agentmods.dev/skills/hec-ovi/research-skill/research"><img src="https://agentmods.dev/badge/skills/hec-ovi/research-skill/research/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/hec-ovi/research-skill/research"><img src="https://agentmods.dev/badge/skills/hec-ovi/research-skill/research.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 | $0.00113 | $0.07482 |
| Opus 5 | $0.00056 | $0.03741 |
| Sonnet 5 | $0.00023 | $0.01496 |
| Haiku 4.5 | $0.00011 | $0.00748 |
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 9d 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.
This is a copy
91% identical to research — 90 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research
Persistent project-scoped store for deep research findings in Codex. You activated this skill because the user asked a substantive research question, or invoked it explicitly with /research <topic>.
If invoked with a topic argument (e.g. /research tailwind-v5), use it as the seed for Retrieval - start by looking up that topic in INDEX.md. Don't research blindly; the lookup may answer immediately.
Four rules carry this skill. They are stated here first because they matter most, and restated at the end:
- Investigations start from zero context. Everything they need goes in one self-contained brief, whether run inline or by a subagent.
- The contrarian pass is mandatory. An investigation without it is incomplete; re-run or fill it yourself.
- The main agent owns all file writes. Investigations return text; only you touch
.research/. - Investigation always ends in Storage. Fresh research that never reaches
.research/is a failed run; verify the write before reporting done.
When to use
- "what's the latest npm package that does X"
- "compare A vs B vs C for 2026"
- "which engines / frameworks / libraries can clone X fast"
- "research how Y works under the hood"
- "deep dive on Z"
- User pastes a long markdown research dump and asks you to save it
When NOT to use
- Plan-stage notes
- Small facts or one-line preferences
- Code-level decisions tied to one file
- Casual lookups answerable from a single source with no synthesis
- Recording personal ideas or musings
- As a substitute for a single focused web search or page fetch
If a single web search + 1-2 sentences answers the question, you don't need this skill.
A subjective or ambiguous question ("best X", "which is better") is not automatically casual: "best" means a comparison across current options, which is exactly what this skill does. Pick the most common reading of the question, state it in one line, and proceed; put alternative readings in ## Open questions. Do not stall by asking the user which variant they meant.
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.
- 9d ago First seen · 415 lines · 0 tokens per session scan A 96507f99d2dd
research is a skill published in the GitHub repository hec-ovi/research-skill (13 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 7,482 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to research, differing in 90 lines, and is treated as a copy.
Other skills, from other repositories
wiki
A persistent Markdown knowledge base maintained by an AI agent. Markdown is a plain-text format for structured notes; the knowledge base can hold personal research or documentation about an open-source project's design.
obsidian-kb
Use this skill when the user wants to build a knowledge base for their project, create an Obsidian wiki from project data, analyze project structure for knowledge management, or mentions "obsidian-kb", "knowledge base", or "compile wiki".
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
higgsfield-troubleshoot
Use when a Higgsfield generation fails, produces poor quality, looks wrong, doesn't match the prompt, or the user needs to fix or improve an output.