Agentmaster review
Skill rhawk117/agentmaster/copilot/skills/agentmaster-review
Claude Code & GitHub Copilot skill. Expensive head, cheap hands, a master decision-maker on a frontier reasoning model that never touches the repository, commanding subagent workers that do all the reading, running, and writing with adversarial gates at both ends.
npx -y skills add rhawk117/agentmaster --skill agentmaster-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 19 days oldThe repository was created 19 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Adversarial code review with the agentmaster evidence pipeline. Use when the user asks for an agentmaster review of a diff, branch, or change set, or invokes /agentmaster-review. Assumes the code is guilty until proven working across correctness, structure, testability, flexibility, and security axes, with severity calibration and adjudicated findings.
SKILL.md
0.9 KB, as published. Nobody here has run it
This skill is a router. The review runs inside the agentmaster-review
custom agent, which carries the frontier model pin and dispatches scout and
code-analyst workers for all evidence.
Invoke the agentmaster-review custom agent now, passing the diff range or
scope verbatim. Do not review inline in this session. If the custom agent is
not available, tell the user to run python install.py install --target copilot from the
agentmaster bundle.
Scope under review: $ARGUMENTS