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 komluk/scaffolding --skill research-methodologygit clone --depth 1 https://github.com/komluk/scaffoldingWrote 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/komluk/scaffolding/research-methodology)<a href="https://agentmods.dev/skills/komluk/scaffolding/research-methodology"><img src="https://agentmods.dev/badge/skills/komluk/scaffolding/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 | $0.00054 | $0.00862 |
| Opus 5 | $0.00027 | $0.00431 |
| Sonnet 5 | $0.00011 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
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 8d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Methodology Skill
Systematic approach for gathering accurate, version-specific documentation before implementation.
Auto-Invoke Triggers
- Implementing specific libraries/APIs
- Requesting current technology documentation
- Verifying API signatures or methods
- Working with external dependencies
- Upgrading framework versions
5-Step Methodology
Step 1: Rapid Assessment (< 30 seconds)
- Extract library/API names from request
- Detect versions from dependency files:
package.json(Node.js)requirements.txt(Python)Cargo.toml(Rust)
- Ask ONE clarifying question if needed
Step 2: Source Prioritization
| Priority | Source | Trust Level |
|---|---|---|
| 1 | Official documentation | HIGH |
| 2 | Migration guides | HIGH |
| 3 | Release notes | HIGH |
| 4 | GitHub repos | MEDIUM |
| 5 | Blogs, tutorials | LOW |
| ❌ | Stack Overflow, AI content | AVOID |
Step 3: Information Retrieval (< 90 seconds)
- Use WebFetch for official documentation URLs
- Use WebSearch to discover official sites
- Extract:
- API signatures
- Setup instructions
- Code examples
- Gotchas/caveats
- Best practices
- 60-second timeout per source
Step 4: Verification & Citation
- Cite EVERY claim with:
- Version number
- Source URL
- Section reference
- Assess confidence:
- HIGH: Official docs, exact version match
- MEDIUM: GitHub, close version
- LOW: Community sources, version mismatch
Step 5: Structured Output
Deliver ResearchPack format:
## ResearchPack: [Library/API Name]
### Quick Reference
- **Library**: name v1.2.3
- **Use Case**: [what we're implementing]
- **Confidence**: HIGH/MEDIUM/LOW
### Key APIs
| Function | Signature | Description |
|----------|-----------|-------------|
| func1 | `func1(arg: Type): Return` | Does X |
| func2 | `func2(arg: Type): Return` | Does Y |
### Setup Steps
1. Install: `npm install library`
2. Configure: ...
3. Import: ...
### Gotchas
- ⚠️ [Common mistake to avoid]
- ⚠️ [Version-specific caveat]
### Code Examples
```typescript
// Example usage
Implementation Checklist
- Install dependencies
- Configure settings
- Import modules
- Implement feature
Open Questions
- [Decision needed for planning phase]
Sources
- Official Docs - v1.2.3, Section X
- GitHub - README
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.
- 8d ago First seen · 137 lines · 54 tokens per session scan A ff566fe56433
research-methodology is a skill published in the GitHub repository komluk/scaffolding (15 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 862 once invoked, about $0.0003 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
turnstile-loop-start
Starts a goal-directed loop run -- asks for mode, initialises state.json, then dispatches loop-runner repeatedly until the success condition is met, max-iterations is reached, or an unrecoverable error occurs.
turnstile-loop-status
Reads turnstile/loops/ /state.json and renders the current phase, status, and full iteration history in the terminal.
turnstile-brain-init
Opt-in bulk bootstrap of turnstile/code/ -- one linked note per source file. The default pipeline is lazy (code notes only for ticket-touched files, written when the ticket passes review); this is the eager exception. Dispatched by /turnstile:brain-init only.
turnstile-brain
Vault layout, the shared note format, and the check-the-brain-first mandate. Auto-loads whenever any turnstile skill starts new work or /turnstile:review is about to commit.
turnstile-conversate
Entry point for natural-language turnstile requests -- classifies the message against board state, then answers directly or invokes the one matching skill (brainstorm, quick, refine, spec, sprint-plan, work, review, breakdown, drop, systematic-debugger, code-reviewer).
turnstile-work
Implements one sprint ticket via TDD and the turnstile-coder agent, checking the brain first. Dispatched by /turnstile:work or conversate routing only.