research-collaborator

research-collaborator is a skill for Claude Code from saidwivedi/research-skills. It costs 108 tokens per session (1,849 once invoked), scanned A, original, MIT.

A research-review assistant for testing, checking, and challenging research ideas, especially in artificial intelligence and machine learning. It investigates code, logs, papers, experiments, and possible causes of failure.

In plain words
What is it for?
Finding related research, reviewing implementations and results, designing experiments, diagnosing failures, and defining conditions that would disprove a hypothesis.
Why use it?
It gives researchers evidence for deciding whether an idea holds up, instead of relying only on intuition or a single result.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the research-collaborator plugin — 1 skill shipped together

Good fit Finding related research, reviewing implementations and results, designing experiments, diagnosing failures, and defining conditions that would disprove a hypothesis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saidwivedi/research-skills/research-collaborator
Install

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.

Any agent
npx skills add saidwivedi/research-skills --skill research-collaborator
Clone the repo
git clone --depth 1 https://github.com/saidwivedi/research-skills

Made for: Claude Code.

Or install research-collaborator, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for research-collaborator

README.md
[![agentmods](https://agentmods.dev/badge/skills/saidwivedi/research-skills/research-collaborator/github.svg)](https://agentmods.dev/skills/saidwivedi/research-skills/research-collaborator)
Your own site
<a href="https://agentmods.dev/skills/saidwivedi/research-skills/research-collaborator"><img src="https://agentmods.dev/badge/skills/saidwivedi/research-skills/research-collaborator/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.

agentmods 80×15 button for research-collaborator

Your own site · 80×15
<a href="https://agentmods.dev/skills/saidwivedi/research-skills/research-collaborator"><img src="https://agentmods.dev/badge/skills/saidwivedi/research-skills/research-collaborator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,849 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00108 $0.01849
Opus 5 $0.00054 $0.00924
Sonnet 5 $0.00022 $0.00370
Haiku 4.5 $0.00011 $0.00185

Measured 11d ago against content hash 376a33c7da77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-collaborator 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 11d 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.

plugins/research-collaborator/skills/research-collaborator/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Collaborator

You are a research collaborator. YOU do the investigative work — reading code, analyzing logs, searching literature, designing experiments, diagnosing failures. The researcher has ideas and makes decisions. You give them the clearest possible basis for those decisions.

Do not hand the researcher checklists or tell them to go search. You search, you read, you analyze, you report back.


Parallel Execution

Maximize use of the Agent tool. Whenever you have 2+ independent tasks, launch parallel agents.

  • Literature search: one agent per query variation (always 3+ variations)
  • Codebase: separate agents for model, data pipeline, training loop, configs
  • Feasibility + prior work + risk assessment: run concurrently
  • Silent bug audit: launch as background agent while doing other work

Do not serialize what can be parallelized.


Rules That Override Your Defaults

These are behaviors you must follow that differ from what you'd do without this skill:

  1. Every hypothesis needs a kill criterion. Before any experiment, write: "This hypothesis is wrong if [specific outcome]." If you can't write one, the idea isn't testable yet.

  2. Record predictions before running. Write: "If correct, I expect [metric] to be [range]." This prevents post-hoc rationalization. Do this every time, no exceptions.

  3. Search 3+ query variations for prior work. Never assess novelty from training knowledge. Use: (a) the idea in its own terms, (b) the mechanism described abstractly, (c) the concept as it appears in adjacent fields. Also search "[problem] negative results." If web search is unavailable, flag: "Novelty assessment without web search — treat as unreliable."

  4. Cheapest killing test first. Never run a full-scale experiment when a 2-hour toy version could falsify the core assumption. Find a fast proxy (5k steps instead of 200k, subset eval, gradient norms as early signal).

  5. One variable at a time. If you can't attribute a result to a specific cause, you've learned nothing. Make changes toggleable via config flags.

Read the full file on GitHub · 183 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 11d ago First seen · 183 lines · 108 tokens per session scan A 376a33c7da77

Subscribe to this mod's changes

research-collaborator is a skill published in the GitHub repository saidwivedi/research-skills (40 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 1,849 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

autoresearch

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…

Orchestra-Research/AI-Research-SKILLs · 98 tokens

astro-dso-doc

Generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), AND a ready-to-paste PixInsight project Description field for a deep-sky object (DSO) astrophotography project. Use this skill whenever the user mentions astrophotography, a DSO…

jjmartres/ai-coding-agents · 244 tokens

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Orchestra-Research/AI-Research-SKILLs · 58 tokens

manuscript-drafter

Draft long-form manuscript sections — abstract, introduction, related work, methods, results, discussion, limitations, conclusion — from a methodology document and an analysis report. Adapts to the target journal's structure (IMRaD, narrative, mixed) and word limits. Preserves the existing manuscript's voice, enforces…

Marazii/research-co-pilot · 202 tokens

talk-builder

Turn a paper (or several, a thesis, a body of work) into an academic talk — outline, per-slide content, speaker notes, opening hook, single take-home message, backup slides for Q&A, rehearsal plan. Adapts to talk length (3-min lightning through 90-min defense), audience (specialists / general field /…

Marazii/research-co-pilot · 238 tokens

data-analysis

End-to-end quantitative data work — cleaning, exploration, statistical testing, modeling, visualization, and reproducible scripting in Python or R. Handles messy CSVs, survey data, time series, panel data, and small-to-medium datasets. Produces analysis scripts and a written interpretation. Trigger when: user mentions…

Marazii/research-co-pilot · 142 tokens