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/komluk/scaffolding/pattern-recognitionnpx skills add komluk/scaffolding --skill pattern-recognitiongit clone --depth 1 https://github.com/komluk/scaffoldingWhat 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 | $0.00058 | $0.01787 |
| Opus 5 | $0.00029 | $0.00894 |
| Sonnet 5 | $0.00012 | $0.00357 |
| Haiku 4.5 | $0.00006 | $0.00179 |
Grade A, and why
pattern-recognition 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 2d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern Recognition Skill
Standards for identifying and applying existing codebase patterns to maintain consistency.
When to Apply
- Before writing new code
- When implementing similar features
- Code review for pattern consistency
- Refactoring decisions
Pattern Detection Process
Step 1: Scan Existing Code
| Action | Purpose |
|---|---|
| Find similar modules/components | Match structure and naming |
| Find similar functions/hooks | Match return types and patterns |
| Find similar services | Match error handling and API patterns |
| Check shared-types location | Match how the project centralizes types |
Step 2: Extract Patterns
| Element | What to Look For |
|---|---|
| Module/component structure | Imports, signature, body order |
| State management | Local-vs-shared state decisions |
| Error handling | Try/catch style, error messages |
| Naming conventions | Files, functions, types |
| File organization | Directory structure |
Step 3: Apply Consistently
| Rule | Description |
|---|---|
| Match existing style | New code follows established patterns |
| Document deviations | If pattern changes, document why |
| Refactor if needed | Update old code to match new pattern |
Example: React + TypeScript conventions (illustrative)
Illustrative — the naming, component, hook, service, and type conventions below are one team's React/TypeScript catalog shown as a concrete example. The reusable skill is the process above (scan → extract → apply existing conventions). Substitute your stack's actual conventions; the value of this skill is matching whatever your codebase already does, not adopting these specific rules.
Naming Conventions
File Naming
| Type | Convention | Example |
|---|---|---|
| Component | PascalCase | AnnotationCard.tsx |
| Hook | camelCase with use | useVisualization.ts |
| Service | camelCase | apiService.ts |
| Types | camelCase or index | types/index.ts |
| Store | camelCase with Store | projectStore.ts |
| Utility | camelCase | formatters.ts |
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.
- 2d ago First seen · 224 lines · 58 tokens per session scan A b076bea4d6ec
pattern-recognition is a skill published in the GitHub repository komluk/scaffolding (15 stars, last pushed 27d ago), licensed MIT. It adds 58 tokens to every session and 1,787 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
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
comfyui-node-registry
Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec, comfy-cli publishing, and CI.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
performance-analysis
Measurement approaches, profiling patterns, bottleneck identification, and optimization guidance. Use when diagnosing performance issues, establishing baselines, identifying bottlenecks, or planning for scale. Always measure before optimizing.
optimize
Self-contained compound loop: read threadsskilllearnings.log, cluster the misses, propose concrete sub-skill rule edits, and apply them with the user's approval. The fourth step after Plan / Work / Review. Trigger words: 'optimize', 'compound', '優化skill', '自我優化', '閉環'.
voice
Deep analysis of user's historical posts and comment replies to build a comprehensive Brand Voice profile. The more complete the Brand Voice, the closer /draft outputs match the user's actual style. Trigger words: 'brand voice', 'voice', '品牌聲音', '語感分析'.