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 olehsvyrydov/AI-development-team --skill research-methodgit clone --depth 1 https://github.com/olehsvyrydov/AI-development-teamWrote 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/olehsvyrydov/ai-development-team/research-method)<a href="https://agentmods.dev/skills/olehsvyrydov/ai-development-team/research-method"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/research-method/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/olehsvyrydov/ai-development-team/research-method"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/research-method.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 | $0.00090 | $0.01359 |
| Opus 5.5 | $0.00036 | $0.00544 |
| Sonnet 5.5 | $0.00018 | $0.00272 |
| Haiku 4.5 | $0.00009 | $0.00136 |
Grade A, and why
research-method 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 today.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigating honestly, and writing it up
An investigation that could only have produced the answer you wanted is not evidence. This skill is about designing work that can come out against you, and reporting it so that a skeptical reader can check.
Design
State the question so it has a wrong answer. "Does structure improve retrieval?" cannot fail. "Does structure-aware retrieval raise exception retention above the 83% ceiling that flat retrieval imposes on every model tier?" can.
Pre-register when the result will be used to decide something. Write hypotheses, effect-size thresholds, and the analysis plan before collecting data, and freeze them. After the freeze, a protocol change is a logged deviation and a deviated run cannot satisfy a gate. This converts the weakness of grading your own homework into a commitment — and publishing the protocol before the run is the single most credibility-earning move available to a solo researcher.
Write kill conditions, and mean them. Every investigation should name what result would make it stop. The best outcome this project has produced was a FID cancelled by its own kill condition — the bake-off showed structure, not model tier, was the lever, so the learned router was never built. A document written so it can be cancelled is worth more than one written to be justified.
Isolate one variable through one pipeline. Every arm should run the same path with only the thing under test swapped, so a difference is attributable. If arms differ in prompt and representation, the result means nothing.
Prefer deterministic verification over model judgement. Symbolic checkers — normalised quantity comparison, verbatim span matching, AST checks — remove judge bias, judge cost, and judge variance, and make every number reproducible from recorded responses. The crude-looking check is often exactly right: where the correct answer is near-extractive, identity-up-to-whitespace is fidelity. When the task stops being extractive (code generation), say so and replace the metric rather than stretching it.
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.
- today First seen · 58 lines · 90 tokens per session scan A 9143f1f21730
research-method is a skill published in the GitHub repository olehsvyrydov/AI-development-team (17 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 1,359 once invoked, about $0.0004 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 2026-10-19.
Other skills, from other repositories
computational-pathology-research
Researches computational pathology and health AI literature using HuggingFace Papers MCP and Exa web search. Use when user says "find papers on", "research", "what's the latest on", "literature review", "survey", or asks about methods like MIL, SSL, WSI analysis, attention-based pooling, patch embedding, weakly…
drug-discovery
Drug discovery: ChEMBL search, drug-likeness, interactions.
build-interactive-explainers
A guide for building interactive explainers, calculators, and simulations driven by an executable model. Users change inputs, steps, states, or events to understand a rule or see how a process develops over time.
arxiv
Search arXiv papers by keyword, author, category, or ID.
aeja-workflow
Use when deciding which aeja- sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for an American Economic Journal: Applied Economics (AEJ: Applied) submission. Routes — it does not replace — the specialized skills.
aejmac-workflow
Use when deciding which aejmac- sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for an American Economic Journal: Macroeconomics (AEJ: Macro) submission. Routes — it does not replace — the specialized skills.