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/wirasm/dylan/context-primegit clone --depth 1 https://github.com/Wirasm/dylanWhat 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 | $0.00000 | $0.00283 |
| Opus 5 | $0.00000 | $0.00142 |
| Sonnet 5 | $0.00000 | $0.00057 |
| Haiku 4.5 | $0.00000 | $0.00028 |
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.
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:
- Read the main README.md to understand the overall purpose and structure
- 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
- 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
- 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
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.
- yesterday First seen · 28 lines · 0 tokens per session scan A acb5bbed3927
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.
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.