The Agent Skills Directory

[SAFE]: The skill defines a structured workflow using persistent local markdown files to maintain state across agent sessions, addressing the volatile memory of standard agent tool calls.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface as it encourages the agent to save research findings to notes.md and subsequently read them to update task plans.
Ingestion points: External research data is stored in notes.md and task_plan.md via the Write and Edit tools, and later read back into context using Read, Grep, or Glob tools.
Boundary markers: The skill does not define specific delimiters or instructions to ignore potentially malicious embedded content within the saved planning files.
Capability inventory: The skill utilizes Read, Write, Edit, Bash, Grep, and Glob tools for file and system interaction.
Sanitization: No explicit content sanitization is described for the information gathered and stored during the research phase.
[SAFE]: The skill provides attribution to upstream sources and relevant technical blogs using standard, plain-text URLs without any signs of obfuscation or impersonation.

planning-with-files