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 saidwivedi/research-skills --skill research-collaboratorgit clone --depth 1 https://github.com/saidwivedi/research-skillsWrote 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/saidwivedi/research-skills/research-collaborator)<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.
<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>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 | $0.00108 | $0.01849 |
| Opus 5 | $0.00054 | $0.00924 |
| Sonnet 5 | $0.00022 | $0.00370 |
| Haiku 4.5 | $0.00011 | $0.00185 |
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.
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:
-
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.
-
Record predictions before running. Write: "If correct, I expect [metric] to be [range]." This prevents post-hoc rationalization. Do this every time, no exceptions.
-
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."
-
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).
-
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.
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.
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.
- 11d ago First seen · 183 lines · 108 tokens per session scan A 376a33c7da77
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.
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…
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…
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.
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…
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 /…
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…