dynamics365ninja

7 mods across 1 repository, 136 stars between them.

eval-author

01

dynamics365ninja/d365fo-mcp-server

Agent Claude Code

Authoring role for the D365FO agent eval loop catalog. Drafts a new eval/cases/ .json spec (valid against eval/cases/schema.json), scaffolds its golden folder, and sets goldenpending until the golden is captured on the VM. Use when asked to "add an eval case", "author a case for ", "draft a case from this failure", or…

136 yesterday A 92 tokens original MIT

eval-implementer

02

dynamics365ninja/d365fo-mcp-server

Agent Claude Code

Implementer role of the D365FO agent eval loop. Runs ON THE VM (mcp-server in full mode + C# bridge) against the Contoso sandbox model. Takes an eval case id, drives the grounded MCP tool path to implement it, builds, scores against the golden/SysTest oracle, writes a corpus record, and rolls back. Use when asked to…

136 yesterday A 104 tokens original MIT

eval-improver

03

dynamics365ninja/d365fo-mcp-server

Agent Claude Code

Improver role of the D365FO agent eval loop. Reads the corpus of run records, ranks failure clusters, reproduces a TOOLDEFECT/KNOWLEDGEGAP/VALIDATORGAP as a minimal VM-free repo test, fixes it, validates against the held-out split, and opens a PR citing corpus evidence. Runs in the repo (never touches the VM). Use…

136 yesterday A 111 tokens original MIT

eval-author

04

dynamics365ninja/d365fo-mcp-server

Command Claude Code

Draft a new eval case (eval/cases/ .json) + scaffold its golden folder, goldenpending until captured on the VM.

136 yesterday A 28 tokens original MIT

eval-improve

05

dynamics365ninja/d365fo-mcp-server

Command Claude Code

Work the eval-loop corpus — rank failure clusters, fix the top actionable defect, validate against held-out, open a PR.

136 yesterday A 25 tokens original MIT

eval-run

06

dynamics365ninja/d365fo-mcp-server

Command Claude Code

Run an eval case end-to-end on the VM (implement → build → score → record → roll back). VM/full-mode only.

136 yesterday A 27 tokens original MIT