The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses several shell commands, including cat, grep, sed, head, and tail, to retrieve and parse session information from local files. It also relies on a platform-specific command octopus state-path to resolve project state locations.
[DYNAMIC_EXECUTION]: The agent is instructed to execute a local script file, ./scripts/octo-state.sh, with specific arguments (read_state, get_context_tier) to manage workflow state. While this script is part of the local project structure, its execution constitutes a dynamic capability.
[INDIRECT_PROMPT_INJECTION]: The skill reads data from project files such as .octo/STATE.md, PROJECT.md, and .octo-continue.md, and incorporates this data into the agent's context. This creates a surface where instructions embedded in these files by an external actor could influence the agent's behavior.
Ingestion points: .octo/STATE.md, .octo/PROJECT.md, and .octo-continue.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the scripts.
Capability inventory: The skill has access to shell command execution and local script invocation.
Sanitization: No sanitization or verification of the content from the restoration files is performed before it is processed by the agent.

skill-resume