The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from multiple local file paths to summarize current work status, creating a potential surface for instructions embedded in project files to influence the agent.
Ingestion points: Processes file listings and content from the todos/, plans/, and docs/solutions/ directories (found in SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when interpolating this data into the summary prompt.
Capability inventory: The skill utilizes shell utilities (ls, git, head) and executes local scripts (./scripts/log-skill.sh, ./scripts/compound-dashboard.sh).
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from these files before it is processed by the agent.
[COMMAND_EXECUTION]: The skill executes local shell commands and vendor-specific scripts to gather context and log usage.
Evidence: Invokes ./scripts/log-skill.sh and ./scripts/compound-dashboard.sh during the instrumentation and health check phases.
Evidence: Uses git log and git status to retrieve repository activity.

session-resume