context-attachment-manager
Reduces token waste and API costs by letting Claude selectively retrieve only relevant images from conversation history instead of re-uploading or carrying f…
Long image chats in Codex and Claude, without the lag. The model manages its own images, pulling back only what it needs, and any image you made before is one search away: just describe what you remember.
- Ask Claude to find a specific screenshot you shared earlier by describing its content.
- Reduce conversation lag by letting Claude manage which images stay active in context.
- Generate code changes while Claude references only the relevant diagrams you uploaded.
Reduces token waste and API costs by letting Claude selectively retrieve only relevant images from conversation history instead of re-uploading or carrying full context. Eliminates performance degradation in extended visual debugging sessions.
Engineering teams conducting long-running code reviews or debugging sessions with screenshot-heavy workflows in Claude or Codex.
https://github.com/chipfighter/context-attachment-manager
By chipfighter
How to Get It
claude plugins install chipfighter/context-attachment-manager
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Find a specific screenshot me shared earlier by describing its content
Trust Signals Auto-scanned
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 338 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 338 GitHub stars; contributors unknown; last commit 0d ago; license MIT.