context-discipline
context-discipline is a Context window & token budget skill for AI agents, published by Resgrid in the Core repository on GitHub. Skillspace rates context-discipline D (55/100) and it passed the safety scan; the rating is based on static analysis only.
Token budget management for Claude Code sessions. Teaches how to minimize context consumption using MCP-first navigation, lazy loading, subagent isolation, and strategic file reading. Keeps Claude effective throughout long sessions by treating the 200k token window as a budget, not a dumping ground. Load this skill when context is running low, sessions feel sluggish, Claude starts forgetting earlier context, or when planning how to explore a large codebase efficiently. Keywords: "context", "tokens", "budget", "running out of context", "too many files", "large codebase", "memory".
- Grade
- D
- Quality
- 55 / 100
- Safety
- Passed
- GitHub stars
- 218
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 84 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Low-risk patterns
- License
- Apache-2.0
- Adoption
- Adopted by 3 other repositories, in 0 collections
- Scope
- Portable: works in any project. General token-budget discipline applicable to any session
What the scanner flagged
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.