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 ralfyishere/rules-with-receipts --skill research-methodologygit clone --depth 1 https://github.com/ralfyishere/rules-with-receiptsWrote 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/ralfyishere/rules-with-receipts/research-methodology)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/research-methodology"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/research-methodology/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/ralfyishere/rules-with-receipts/research-methodology"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/research-methodology.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 | $0.00093 | $0.01611 |
| Opus 5 | $0.00046 | $0.00805 |
| Sonnet 5 | $0.00019 | $0.00322 |
| Haiku 4.5 | $0.00009 | $0.00161 |
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 9d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Methodology
Purpose
Research fails in a characteristic way: one search angle, the first three convincing sources, a confident synthesis — which is really the loudest narrative in the index, not the state of the truth. This skill is the acquisition process: how to search from multiple angles, when sources count as independent, when to stop, and how to report what the research does and doesn't cover. (verification-discipline governs how the resulting claims are labeled; this governs how they're gathered.)
When to use this skill
- Questions answered by assembling external sources: markets, tools, techniques, prior art, "what's known about X".
- Comparisons where the options' claims about themselves are part of the evidence problem.
- Any deliverable that will cite sources — the citing standard starts at collection time.
When NOT to use this skill
- Single stable facts — one reliable source and done.
- Questions answerable from provided material (
live-state-truth: read it) or by direct observation/derivation (run it, compute it) — observation beats testimony; don't research what you can check. - Pure reasoning tasks —
structured-reasoning— though hybrids are common (research the inputs, then reason).
Operating procedure
1 — Decompose the question into sub-questions with answerable form (deep-decomposition): "Is X better than Y?" becomes "What does X/Y each claim? What do practitioners report? What are the failure stories? What's the cost structure?"
2 — Plan the search angles before searching. Multiple vocabularies (the marketing term, the academic term, the practitioner slang, the error message), multiple source types — vendor/official docs, practitioner reports (forums, postmortems, issue trackers), data (benchmarks, filings), and critics. Any question researched through only one source type inherits that type's bias wholesale.
3 — Apply the independence rule. Load-bearing claims need 2+ independent sources. Independent means: not citing each other, not derived from the same press release/paper/announcement, not the same author twice. Twenty articles tracing to one origin are one source with good SEO — this is citation laundering, and detecting it (check who cites whom, look for identical phrasings) is a core research act.
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.
- 9d ago First seen · 73 lines · 93 tokens per session scan A 9ee6f8dc9e2e
Research Methodology is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 1,611 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 2026-08-31.
Other skills, from other repositories
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
frontend-design
A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.
alterlab-cobrapy
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…
alterlab-depmap
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use when identifying cancer-specific genetic vulnerabilities, finding synthetic lethal interactions, checking whether a gene is essential in given cell lines, or…
alterlab-qutip
Simulates open quantum systems with QuTiP, the Quantum Toolbox in Python, solving Lindblad master equations (mesolve), Monte Carlo trajectories (mcsolve), and unitary dynamics (sesolve). Use when studying master-equation or Lindblad dynamics, decoherence, dissipation, quantum optics, cavity QED, or open-system time…