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 GiangGiangTran/ba-skills --skill pattern-recognitiongit clone --depth 1 https://github.com/GiangGiangTran/ba-skillsWrote 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/gianggiangtran/ba-skills/pattern-recognition)<a href="https://agentmods.dev/skills/gianggiangtran/ba-skills/pattern-recognition"><img src="https://agentmods.dev/badge/skills/gianggiangtran/ba-skills/pattern-recognition.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 | $0.00038 | $0.02063 |
| Opus 5 | $0.00019 | $0.01032 |
| Sonnet 5 | $0.00008 | $0.00413 |
| Haiku 4.5 | $0.00004 | $0.00206 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern Recognition for BA
What do the numbers show? What's really happening?
What is Pattern Recognition?
Definition: Identifying recurring themes, anomalies, and trends across data sets, interviews, or documents - finding the signal in noise.
Why it matters:
- Hidden patterns: One-off observation vs actual trend
- Outlier detection: Which observations are unusual/important?
- Data-driven insights: "Many users said it" vs "A few users said it"
- Contradiction detection: "Users love feature X" but "Nobody uses feature X"
- Trend identification: Direction of change (improving/declining)
When to Use:
- ✅ Analyzing 5-8 user interviews (find common themes)
- ✅ Reviewing customer feedback (what's most mentioned?)
- ✅ Analyzing data sets (what's the trend?)
- ✅ Finding inconsistencies (why do findings conflict?)
- ✅ Identifying root causes (what's the common factor?)
3 Pattern Types
Type 1: Frequency Patterns (The 60% Rule)
What appeared in 60%+ of observations?
Interview Finding: "Users find setup confusing"
Count appearances:
Interview 1: User said "setup confusing" ✓
Interview 2: User said "takes too long" ✓
Interview 3: User said "confusing" ✓
Interview 4: User completed easily ✗
Interview 5: User said "confusing" ✓
Interview 6: User said "unclear" ✓
Interview 7: User completed in 5 min ✗
Interview 8: User said "complex" ✓
Count: 6 out of 8 mentioned confusion = 75%
→ PATTERN FOUND (60%+ threshold)
Conclusion: Setup confusion is widespread issue,
not just one user's problem
Type 2: Contradiction Patterns
What conflicts with other observations?
Observation 1: "Users love the dashboard feature"
- Quote 1: "Dashboard gives me visibility I need"
- Quote 2: "Dashboard is my favorite feature"
But Data Shows: Dashboard usage is only 15% of users
80% never open dashboard
CONTRADICTION FOUND!
→ Investigation: Maybe users love it when they use it,
but most don't discover it or use it
(awareness/discoverability problem, not feature problem)
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 · 320 lines · 38 tokens per session scan A 0004bd20bb6c
pattern-recognition is a skill published in the GitHub repository GiangGiangTran/ba-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 2,063 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…