Tool-agnostic agentic coding setup: 30 agents, 55 skills, 74 rules, 33 commands, 7 hooks, MCP servers, and a CLI-tool surface generated for 3 AI coding tools from a single canonical source. Counts derived from governance/inventory.json.
★not rated 26 21d agoA
tokens not measured
originalMIT
AI feature evaluation, prompt versioning, cost telemetry, prompt caching, model fallback, and hallucination-as-SLI for end-user projects shipping LLM features.
P8 B1 floor: every hatch3r-invoked agentic workflow detects and resolves ambiguity via the platform-native question tool BEFORE executing — default behavior, not exception-driven. Names the 5-trigger set and mandates a §0 ambiguity gate on every mutating agent, command, and skill.
Operator-facing chat register for hatch3r agents — two registers keyed off the manifest communicationStyle scalar (plain, the default, or technical): the plain register mandates an outcome-first headline (≤3 facts before detail), first-use glosses for acronyms/ids/tier-pillar vocabulary, sentences averaging ≤25 words…
Shared-contract discipline for brownfield changes — contract taxonomy, repo-wide consumer census as lane-exit gate, seam-owner protocol for parallel lanes, façade contract-hold on field drop/rename, value-drift census for shared constants.
Shared output frame for the CQ measurement rules — the per-finding rigor-field schema and the Specialist-Status to canonical-severity map cited by hatch3r-{security,testability,scalability,maintainability,enhancability}.
★not rated 26 21d agoA0 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: