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 commands/dotclaude/marketplace/pattern_discoverygit clone --depth 1 https://github.com/dotclaude/marketplaceWhat 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 | $0.00009 | $0.04001 |
| Opus 5 | $0.00005 | $0.02001 |
| Sonnet 5 | $0.00002 | $0.00800 |
| Haiku 4.5 | $0.00001 | $0.00400 |
Grade A, and why
pattern_discovery 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern Discovery Engine
Identify deep structural patterns across domains, recognize recurring frameworks, and facilitate pattern transfer for enhanced problem-solving and understanding. Transform seemingly unrelated information into coherent pattern libraries that reveal universal principles and enable innovative applications.
Pattern Category Framework
Structural Patterns (Organizational and architectural patterns)
[Extended thinking: Identify how components organize, relate, and create stable arrangements across different contexts and domains.]
Architectural Organization:
- Hierarchical Structures: Tree-like organizations with clear parent-child relationships
- Network Topologies: Interconnected nodes with distributed relationships and flows
- Layered Architectures: Stratified systems with abstraction levels and interfaces
- Modular Systems: Component-based organizations with defined boundaries and interactions
- Fractal Patterns: Self-similar structures that repeat at different scales
Relationship Patterns:
- Dependency Chains: Sequential relationships where elements depend on predecessors
- Feedback Loops: Circular relationships where outputs influence inputs
- Hub-and-Spoke: Central nodes that coordinate distributed peripheral elements
- Mesh Networks: Distributed connectivity with multiple pathways and redundancy
- Pipeline Flows: Sequential processing stages with defined inputs and outputs
Stability Mechanisms:
- Balance Points: Equilibrium states that systems naturally seek
- Tension Resolution: How opposing forces create stable dynamic states
- Adaptation Protocols: Mechanisms that maintain structure while enabling change
- Boundary Maintenance: How systems preserve identity while interacting with environment
- Recovery Patterns: How systems restore stability after disruption
Behavioral Patterns (Process and interaction patterns)
[Extended thinking: Recognize recurring sequences of actions, interactions, and transformations that create predictable outcomes.]
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 · 357 lines · 9 tokens per session scan A 315edee9e457
pattern_discovery is a command published in the GitHub repository dotclaude/marketplace (42 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 4,001 once invoked, about $0.0000 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.