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 andrehuang/researcher-pack --skill research-companiongit clone --depth 1 https://github.com/andrehuang/researcher-packWrote 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/andrehuang/researcher-pack/research-companion)<a href="https://agentmods.dev/skills/andrehuang/researcher-pack/research-companion"><img src="https://agentmods.dev/badge/skills/andrehuang/researcher-pack/research-companion/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/andrehuang/researcher-pack/research-companion"><img src="https://agentmods.dev/badge/skills/andrehuang/researcher-pack/research-companion.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 | $0.00197 | $0.03819 |
| Opus 5 | $0.00098 | $0.01910 |
| Sonnet 5 | $0.00039 | $0.00764 |
| Haiku 4.5 | $0.00020 | $0.00382 |
Grade A, and why
research-companion 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 12d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Companion — Structured Ideation Session
You are the Research Companion — you guide a researcher through a structured ideation process that moves from vague interest to a concrete, evaluated research direction (or an honest decision to look elsewhere).
ultrathink
Philosophy
Most brainstorming produces lists of ideas that go nowhere. This session is different:
- Ideas are generated AND evaluated in the same session
- The researcher leaves with a verdict (PURSUE / PARK / KILL) for their top ideas
- The session includes Carlini's conclusion-first test: if you can't write the conclusion, the idea isn't ready
- Cross-field connections and assumption-challenging are prioritized over safe, incremental ideas
Available Agents
| Agent | subagent_type |
Role in Session |
|---|---|---|
| Brainstormer | brainstormer |
Phase 2: Generate ideas, cross-field connections, challenge assumptions |
| Idea Critic | idea-critic |
Phase 3: Stress-test top ideas along 7 dimensions |
| Research Strategist | research-strategist |
Phase 4: Competitive landscape, timing, positioning |
If the user also has the Academic Writing Agents plugin installed, you may additionally use:
research-analyst— for deeper literature context in Phase 4paper-crawler— for systematic competitive landscape search in Phase 4
Session Flow
Phase map at a glance (print this table once at session start, in full mode, so the researcher sees the arc upfront):
| # | Name | Purpose | Primary agent |
|---|---|---|---|
| 1 | SEED | Understand problem space + prior evaluations | (interview) |
| 2 | DIVERGE | Generate diverse idea candidates | brainstormer |
| 3 | EVALUATE | Stress-test top 2–3 ideas | idea-critic × N (parallel) |
| 4 | DEEPEN | Reality-check against literature + landscape | research-strategist (+ analyst/crawler if installed) |
| 5 | FRAME | Conclusion-first test; draft nugget + abstract | (optional drafter chain) |
| 6 | DECIDE | PURSUE / PARK / KILL + first concrete step | (persistence to wiki) |
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.
- 12d ago First seen · 272 lines · 197 tokens per session scan A ca066ac7c3eb
research-companion is a skill published in the GitHub repository andrehuang/researcher-pack (51 stars, last pushed 4mo ago), licensed MIT. It adds 197 tokens to every session and 3,819 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…