The Agent Skills Directory

[COMMAND_EXECUTION]: The skill manages the just command runner, which executes shell commands defined in Justfile recipes. It also instructs the agent to execute a local TypeScript linting tool using the bun runtime.
[EXTERNAL_DOWNLOADS]: The documentation includes instructions for downloading the just binary from its official website (https://just.systems/install.sh).
[REMOTE_CODE_EXECUTION]: The installation guide describes a pattern of piping a remote script from just.systems (the official domain for the tool) directly into bash for installation.
[DYNAMIC_EXECUTION]: The skill utilizes a local script (Tools/lint.ts) to perform structural validation of files at runtime. It also provides patterns for Justfiles that use backtick evaluation to execute shell commands during the parsing phase.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted Justfiles from a user's project directory while possessing significant capabilities.
Ingestion points: Reads Justfile and .just module files from the project directory as referenced in SKILL.md and Workflows/CheckJustfile.md.
Boundary markers: None; the skill does not define specific delimiters or instructions to ignore content within the files it processes.
Capability inventory: The skill uses Bash, Write, Edit, Grep, and Glob tools as defined in the SKILL.md frontmatter.
Sanitization: No sanitization or validation of the text content within the Justfiles is performed before the agent processes or lints them.

justfile