recursive-context-pruning-token-budgeting
recursive-context-pruning-token-budgeting is a Context window & token budget skill for AI agents, published by sickn33 in the agentic-awesome-skills repository on GitHub. Skillspace rates recursive-context-pruning-token-budgeting D (65/100) and the safety scan flagged it for review; a judge model has also reviewed it.
Flagged for review. Read the source before running it.
Optimizes AI agent performance by pruning redundant context, managing token usage, and enforcing ultra-concise, direct-to-value responses.
- Grade
- D
- Quality
- 65 / 100
- Safety
- Needs review
- GitHub stars
- 43,345
Placed #5 of 6 in the judged category final for Context window & token budget.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 94 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Medium-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 1 collections
- Scope
- Portable: works in any project. General agent context-pruning and token-budgeting discipline
Judge review
Placed #5 of 6 in the judged category final for Context window & token budget.
- Trigger
55 55 - Instructions
45 45 - Specificity
55 55 - Safety
78 78 - Disclosure
65 65 - Maintenance
55 55
Mixes an ungrounded, oddly specific 30/20/50 percent token-allocation rule with unrelated response-tone policing, though it does include a sound anti-jailbreak caveat about not pruning system instructions.
What the scanner flagged
- reads environment variables
- mentions secrets in text
Not checked yet
- 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.