agent-context-management
agent-context-management is a Context window & token budget skill for AI agents, published by nickvasilescu in the nicks-stack repository on GitHub. Skillspace rates agent-context-management B (83/100) and it passed the safety scan; the rating is based on static analysis only.
Use when diagnosing, comparing, or tuning an AI agent's context window, token budget, output reserve, automatic compaction threshold, or provider-specific context cap. Separates model capability from route limits and client bookkeeping, verifies live metadata before editing config, and prevents unsafe fake context-length overrides.
- Grade
- B
- Quality
- 83 / 100
- Safety
- Passed
- GitHub stars
- 73
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
- 100 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- Low-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Portable: works in any project. General AI agent context-window and token budget tuning
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.