Context Visualization
PassAudited by ClawScan on May 1, 2026.
Overview
The skill is purpose-aligned and transparent, but it does read local workspace and memory files to produce token and inventory summaries.
This looks safe for its stated purpose. Before installing, be aware that it summarizes local workspace and memory files; use it only in workspaces where revealing file-size and memory-category metadata is acceptable.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If invoked, the helper will inspect the selected workspace to calculate token estimates.
The skill asks the agent to run a bundled local helper script against a workspace path. This is disclosed and central to the purpose, but users should understand it executes local code and reads files under the chosen workspace.
python3 scripts/estimate_tokens.py /path/to/workspace
Run it only against the intended workspace and avoid pointing it at unrelated directories.
The resulting report can reveal what kinds of memory categories exist and their approximate sizes.
The script recursively reads text files under workspace/memory to estimate token totals and group them by category. It does not print file contents, but it does expose summary metadata about persistent memory.
for root, dirs, files in os.walk(memory_dir): ... content = f.read()
Use this only when you are comfortable showing a memory inventory summary, and add exclusions if some memory categories should remain private.