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 PracticalSwan/agent-skills --skill meta-pattern-recognitiongit clone --depth 1 https://github.com/PracticalSwan/agent-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/practicalswan/agent-skills/meta-pattern-recognition)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/meta-pattern-recognition"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/meta-pattern-recognition/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/practicalswan/agent-skills/meta-pattern-recognition"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/meta-pattern-recognition.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 | $0.00017 | $0.00925 |
| Opus 5 | $0.00009 | $0.00463 |
| Sonnet 5 | $0.00003 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
meta-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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-Pattern Recognition
Overview
When the same pattern appears in 3+ domains, it's probably a universal principle worth extracting.
Core principle: Find patterns in how patterns emerge.
Quick Reference
| Pattern Appears In | Abstract Form | Where Else? |
|---|---|---|
| CPU/DB/HTTP/DNS caching | Store frequently-accessed data closer | LLM prompt caching, CDN |
| Layering (network/storage/compute) | Separate concerns into abstraction levels | Architecture, organization |
| Queuing (message/task/request) | Decouple producer from consumer with buffer | Event systems, async processing |
| Pooling (connection/thread/object) | Reuse expensive resources | Memory management, resource governance |
Process
- Spot repetition - See same shape in 3+ places
- Extract abstract form - Describe independent of any domain
- Identify variations - How does it adapt per domain?
- Check applicability - Where else might this help?
Example
Pattern spotted: Rate limiting in API throttling, traffic shaping, circuit breakers, admission control
Abstract form: Bound resource consumption to prevent exhaustion
Variation points: What resource, what limit, what happens when exceeded
New application: LLM token budgets (same pattern - prevent context window exhaustion)
Red Flags You're Missing Meta-Patterns
- "This problem is unique" (probably not)
- Multiple teams independently solving "different" problems identically
- Reinventing wheels across domains
- "Haven't we done something like this?" (yes, find it)
Remember
- 3+ domains = likely universal
- Abstract form reveals new applications
- Variations show adaptation points
- Universal patterns are battle-tested
Cross-Client Portability
This skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.
- GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the workflow in project instructions when folder discovery is unavailable.
- Claude Code: keep the folder in a local skills directory or a compatible plugin source.
- Codex: install or sync the folder into
$CODEX_HOME/skills/meta-pattern-recognitionand restart Codex after major changes.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed f314d1937175
- 3d ago Changed 1c806192bc52
- 6d ago First seen · 103 lines · 17 tokens per session scan A 173362fb4f06
meta-pattern-recognition is a skill published in the GitHub repository PracticalSwan/agent-skills (13 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 925 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 2026-09-03.
Other skills, from other repositories
antigravity-skill-orchestrator
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
pentest-playbook
7-phase pentest pipeline from passive recon to exploitation.
google-dorks-catalog
High-precision Google dorks for exposed configs, secrets, and credentials -- real-world validated.