What it doesAI
Smart context compression for DSH — managing cognitive resources in limited windows so agents remember what matters.
- Context compression for limited windows
- Manages cognitive resources for LLM agents
- Helps agents remember important information
AI-generated from the repo README — for reference only.
Installation
dsh plugin --profile web add github:Whatsmore-nf/dsh-context-stewardInstall method: GitHub · not yet tested in container (L3+)
Compatibility
| DSH Version | Status |
|---|---|
| not stated | Declared — not tested |
Requirements
- • Node.js: not stated
- • DSH: declared "not stated"
- • External credentials: none detected
Security Report
Automated static scan, not manual review.
No critical or warning findings in the automated scan. The result is valid only for the commit hash shown.
0.20.0dsh manifest0d2bcd24ce732026-08-200d2bcd24ce73The scan result is valid for the scanned commit. New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.
Disclaimer: automated static analysis, not a security guarantee. Always review what you install.
vet verdict: vet: clean · score 62
- R9 · medium [likely] — 正则嵌套量词（ReDoS 风险：(a+)+ 类指数回溯）
- R9 · medium [likely] — 正则嵌套量词（ReDoS 风险：(a+)+ 类指数回溯）
- R9 · info [heuristic] — 循环内 += 累加（字符串拼接可能 O(n²)）
- R9 · info [heuristic] — 循环内 += 累加（字符串拼接可能 O(n²)）
- R9 · medium [likely] — 正则嵌套量词（ReDoS 风险：(a+)+ 类指数回溯）
vet is advisory and does not change dsh’s four-tier level.
• Static heuristic scan: done (12 files)
• Dependency vulnerabilities: requires deep audit (L3+)
• Permission sandboxing: requires runtime testing (L4+)
Activity
Last commit 2026-08-20 · activity: Active
• Repo created: 2026-08-20
• Stars: ★ 1 · Forks: 0
• Health: Active — committed within last 30 days