Before an agent acts on a plan, verify that the things it named actually exist.
Checks each referenced file path, function or method, import or package, environment variable, and CLI command against your repo, and flags the ones that do not resolve. Catches the hallucinated function and the phantom package before the edit, not after the build breaks. Resolves Python and JavaScript/TypeScript.
Get it on Agensi and run it with any agent that reads SKILL.md, such as Claude Code, Codex, or Cursor. The listing includes setup steps and exactly what it reads.
Works with any assistant that reads the open SKILL.md standard. Not locked to a single tool or vendor.
Before an agent acts on a plan, verify that the things it named actually exist. Checks each referenced file path, function or method, import or package, environment variable, and CLI command against your repo, and flags the ones that do not resolve.…
Before an agent acts on a plan, verify that the things it named actually exist. Checks each referenced file path, function or method, import or package, environment variable, and CLI command against your repo,….
Do not treat a successful run as proof beyond the supplied files, declared scope, and evidence the skill actually checked.
Before an agent acts on a plan, verify that the things it named actually exist.
It works with anything that reads SKILL.md, so it is not tied to one tool or vendor.
Current price and purchase option are shown on Agensi. Instant download. Works with any agent that reads SKILL.md.
Get Reference Grounding Checker on Agensi