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 agentmods add skills/chekusu/wanman/research-methodologynpx skills add chekusu/wanman --skill research-methodologygit clone --depth 1 https://github.com/chekusu/wanmanWrote 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/chekusu/wanman/research-methodology)<a href="https://agentmods.dev/skills/chekusu/wanman/research-methodology"><img src="https://agentmods.dev/badge/skills/chekusu/wanman/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 | $0.00020 | $0.00519 |
| Opus 5 | $0.00010 | $0.00260 |
| Sonnet 5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
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 6d 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.
What it actually says
Research Methodology
Core Principles
Every data point must have a source and confidence score. Estimates are not facts — label them as estimates.
Data Source Hierarchy
| Tier | Source Type | Confidence Range | Examples |
|---|---|---|---|
| 1 | Official public data | 0.85-0.95 | Government statistics, public company filings, industry association reports |
| 2 | Authoritative media | 0.70-0.85 | Major financial media, industry analysis reports |
| 3 | Web search results | 0.50-0.70 | Blogs, forums, review sites |
| 4 | Model inference/estimates | 0.20-0.50 | Extrapolations from known data, analogical estimates |
| 5 | Training data memory | 0.10-0.30 | Data from model memory (may be outdated) |
Search Strategy
- Search before estimating: Do not guess from training data if the information can be searched
- Cross-validate: Confirm key data from at least 2 independent sources
- Label timeliness: Note the time range of data (e.g., "2024 data")
- Distinguish facts from opinions: Clearly label when quoting
Data Recording Format
Use wanman artifact put to record each research data point:
# Good recording practice
wanman artifact put --kind market_data --path "competitors/cafe_a/pricing" \
--meta '{"source":"web_search:dianping.com","confidence":0.65,"data_date":"2024-12","avg_price":35,"currency":"CNY","category":"specialty_coffee"}'
# Bad practice (missing source and confidence)
wanman artifact put --kind market_data --path "competitors/pricing" \
--meta '{"avg_price":35}'
Common Pitfalls
- Survivorship bias: Successful cases found via search do not represent the full industry picture
- Outdated data: Rent and foot traffic data from 2 years ago may have changed significantly
- Regional differences: Tier-1 city data cannot be directly applied to tier-2 or tier-3 cities
- Currency/unit confusion: Always label currency and measurement units
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.
- 6d ago First seen · 49 lines · 20 tokens per session scan A f7045ad7a0ae
research-methodology is a skill published in the GitHub repository chekusu/wanman (682 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 519 once invoked, about $0.0001 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
edgeone skill scanner
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.
skill-creator-linter
Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xmlescape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.
paper-abstract-author
Write the abstract after the paper body has been revised, using the final claims and evidence.
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.