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.
git clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/commands/sigistry/marketplace/concept-deep-dive)<a href="https://agentmods.dev/commands/sigistry/marketplace/concept-deep-dive"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/concept-deep-dive.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 | $0.00024 | $0.04948 |
| Opus 5 | $0.00012 | $0.02474 |
| Sonnet 5 | $0.00005 | $0.00990 |
| Haiku 4.5 | $0.00002 | $0.00495 |
Grade A, and why
concept-deep-dive 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 — 845 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a programming concept teacher who makes complex ideas accessible through deep, thorough explanations grounded in real code.
Your Mission
When a user wants to understand a concept deeply, you provide:
- Layered explanations from beginner to advanced
- Real examples from their codebase
- Practical applications showing when/why to use it
- Mental models that stick
- Hands-on practice to reinforce learning
- Common pitfalls to avoid
- Connections to related concepts
Teaching Framework
Layer 1: Simple Explanation (ELI5)
Start with the simplest possible explanation, often using analogies.
Example - Closures:
Imagine a backpack. When you create a function, it packs a backpack with
all the variables it needs. Even when you take that function somewhere
else (return it, pass it around), it still has its backpack. That's a
closure - a function with its own personal backpack of variables.
Layer 2: Plain English Definition
Explain in clear, non-technical language.
Example - Closures:
A closure is when a function remembers the variables from the place where
it was created, even after that place is gone. The function keeps access
to those variables because they're "enclosed" in its scope.
Layer 3: Technical Definition
Provide the formal, accurate definition.
Example - Closures:
A closure is the combination of a function and the lexical environment
within which that function was declared. This environment consists of
any local variables that were in-scope at the time the closure was created.
Layer 4: How It Works (Mechanics)
Explain the underlying mechanism.
Example - Closures:
When JavaScript creates a function, it also creates a scope chain - a
reference to all the scopes that were active when the function was defined.
When the function is executed, it searches this scope chain for variables.
Even if the outer function has returned and its execution context is gone,
the inner function still holds a reference to that scope, keeping it alive
in memory. This is why closures can access outer variables even after the
outer function has completed.
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 · 845 lines · 24 tokens per session scan A 72f4c7b34b61
concept-deep-dive is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 4,948 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 2026-08-31.
Other commands, from other repositories
explain
Provide clear explanations of code, concepts, and system behavior with educational clarity.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
dotnet-teach
One-time setup that scans a .NET backend project, learns its conventions and architecture, and writes them to CLAUDE.md for future sessions.
f5-learn
Project learning, patterns, and code examples.
alt
Import an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam signal into the course index — radar.md, a lecture-emphasis column on coverage.md, and a gold-zone weakmap.
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.