context-prime

A repository-reading command that builds an overview of a codebase by examining its main documentation, experimental concepts, implemented command-line tools, and contributor guidelines.

In plain words
What is it for?
Use it to review a repository’s purpose, directory structure, experimental utilities, production implementations, and documented development rules.
Why use it?
It helps an agent understand how the project is organized and how its parts relate before making changes. The input does not specify any code-writing or modification capability.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/wirasm/dylan/context-prime
Clone the repo
git clone --depth 1 https://github.com/Wirasm/dylan

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 283 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00283
Opus 5 $0.00000 $0.00142
Sonnet 5 $0.00000 $0.00057
Haiku 4.5 $0.00000 $0.00028

Measured yesterday against content hash acb5bbed3927, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-prime 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 yesterday.

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.

.claude/commands/context-prime.md · 28 lines

What it actually says

Please read through the key files in this repository to understand its structure and purpose.

This repository is a concept library for building Claude Code CLI utilities. We explore whats possible with claude code in the concept_library/ directory. building minimal wrappers with 0 to minimal validation.

improve step by step, and if we like the concept in the concept_library/ directory, we move it to the dylan/ directory and build it into the main CLI.

Follow these steps:

  1. Read the main README.md to understand the overall purpose and structure
  2. Explore the concept_library/ directory briefly to understand the concepts being developed
    • For each subdirectory in concept_library/, identify its specific purpose
    • Note how each concept is implemented as a standalone utility
  3. Examine the dylan/ directory more deeply to see the implemented CLI utilities
    • Understand how these are more refined implementations of concepts
    • Look for patterns in how concepts transition from experimental to production
  4. Review CLAUDE.md for specific guidelines on working with this codebase

After analyzing these files, provide a summary of:

  • The repository's purpose and design philosophy
  • The key concepts being explored in concept_library/
  • The purpose of each directory within the repository
  • How the dylan/ directory implements these concepts
  • How these components work together
  • What tasks I might be working on based on recent commits
Changes

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.

  1. yesterday First seen · 28 lines · 0 tokens per session scan A acb5bbed3927

Subscribe to this mod's changes

context-prime is a command published in the GitHub repository Wirasm/dylan (37 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 283 tokens. 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.