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 ntaffzii/Skill-Agents --skill research-methodologygit clone --depth 1 https://github.com/ntaffzii/Skill-AgentsWrote 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/ntaffzii/skill-agents/research-methodology)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/research-methodology"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/research-methodology.svg" alt="Measured on agentmods" 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 | $0.00130 | $0.01157 |
| Opus 5 | $0.00065 | $0.00579 |
| Sonnet 5 | $0.00026 | $0.00231 |
| Haiku 4.5 | $0.00013 | $0.00116 |
Grade A, and why
research-methodology 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 7d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Methodology
Overview
Ad hoc research — search, read the first few plausible results, summarize — is fast but has a specific, recurring failure mode: it stops as soon as something sounds right, not when the question is actually answered, and it can't tell "three sources agree" from "three sources repeating the same original claim" (an echo chamber, not corroboration). This skill is the discipline layer that runs before searching — claim-citation-check is the equivalent check that runs after, on the draft. Together they bracket a research task; this skill alone does not verify anything, it structures how the searching happens.
When to use
- ก่อนเริ่มค้นข้อมูลสำหรับ research report, news brief, หรือ skill/project comparison
- The question has room for real disagreement between sources, or the topic is unfamiliar enough that "what counts as a good source" isn't obvious
- Before
daily-news-report,github-skill-research, orproject-discoverystarts synthesizing — run this first, not as an afterthought
When NOT to use
- A quick factual lookup with one obvious, uncontested source (a library's version number, a function's signature) — the overhead isn't worth it
- The task is synthesis/writing from sources already gathered — that's
markdown-report's job; this skill is specifically about the searching phase
Core knowledge
1. Frame the question before searching. A vague question ("tell me about X") produces a vague, first-plausible-result search. Narrow it to something a search can actually resolve ("what does X's official docs say the default timeout is, as of the current major version") before running the first query.
2. Decide source-quality tiers up front, not after finding something.
| Tier | Examples | Weight |
|---|---|---|
| Primary / official | Vendor docs, source code, the standard's own spec, a repo's own README | Highest — treat as ground truth unless contradicted by newer official source |
| Maintained secondary | Actively-updated community docs, a maintainer's own blog post, a well-cited technical writeup | Medium — good corroboration, not a substitute for checking primary when it matters |
| Unverified / aggregator | Random blog posts, forum answers, SEO content, an AI-generated summary of the topic | Lowest — fine for orientation, never the sole basis for a specific factual claim |
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.
- 7d ago First seen · 55 lines · 130 tokens per session scan A e06d996710ba
research-methodology is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed 5d ago), licensed MIT. It adds 130 tokens to every session and 1,157 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
pake
Package any website or local web build into a lightweight desktop app using Pake (Tauri/Rust). Use when the user wants to: wrap a URL as a native app, build a desktop app from a website or a local dist/ folder, use Pake CLI to package a page, set up proxy for a packaged app, customize app icons or bundle IDs, or…
acceptance
End-to-end verification and self-evidence for a delivery in any repository, with or without a preconfigured verify plan. Discover an existing plan when one was handed to this run; otherwise author checks and publish a standalone acceptance. Pick the proving surface (CLI / web / desktop / iOS Simulator), drive the real…
therapeutic-ifs
Unified inner work engine: Schema deconstruction (diagnosis) + IFS therapy (treatment). Absorbs: schema-deconstruction.
dashboard-builder
Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.
red-team-review
Unified adversarial review: v4.3 Strategic Matrix (MTA-004). 7-phase framework: Priors → Rubric → Adversarial Lenses → SWOT/TOWS → MCDA Decision Engine → Blind Spot/Kill Switch → Executive Summary. Absorbs: bias-detector.