luanmorenommaciel/uc-transact-co
MCP server Claude CodeCodexCursor +2
MCP server "transactco-cfo" as configured in luanmorenommaciel/uc-transact-co. Runs locally from the python Python package.
luanmorenommaciel/uc-transact-co
Skill Claude CodeCodex
Regenerate the structural skeleton of a harness — agent role stubs, KB layout, and per-stack rule files — for a repository's stack, in seconds. Use when a harness structure must be (re)created from artifacts on disk, after the roles and contract are already understood and never before. Produces structure only: every…
luanmorenommaciel/uc-transact-co
Skill Codex
Turn an ambiguous question about an unfamiliar or brownfield system into a bounded, read-only, evidence-backed investigation with a confirmed investigation contract, deliberate context manifest, claim ledger, ontology, owned open questions, and reviewable technical brief. Use when asked to investigate a repository…
luanmorenommaciel/uc-transact-co
Skill Claude CodeCodex
Turn one reasonable-looking plan item into a single atomic Task-Spec that states its goal, the behaviour a named human signs, and the machine-runnable proof that answers "am I done?" without asking. Use when a backlog item, plan row, or ticket permits more than one defensible implementation; before handing work to an…
Plugin Claude Code
Bundles 3 skills, 5 hooks · 209 tokens together
Type-aware, evidence-backed reading and delivery for AI coding agents.
luanmorenommaciel/kimi-plugin-cc
Command Claude Code
Adversarial review that pressure-tests the design, not just the code.
luanmorenommaciel/kimi-plugin-cc
Command Claude Code
Read-only codebase exploration and architecture analysis.
luanmorenommaciel/kimi-plugin-cc
Command Claude Code
Generate a structured implementation plan from a task description — read-only.
luanmorenommaciel/kimi-plugin-cc
Command Claude Code
Structured code review of current changes (optionally against a base ref) — read-only.
luanmorenommaciel/kimi-plugin-cc
Command Claude Code
Execute a tasks/T-.md spec — implement, verify with its Exit Check, report.
luanmorenommaciel/kimi-plugin-cc
Skill Claude CodeCodex
The crank-loop methodology — a measured, iterative loop for delegating implementation tasks to an agent with specs, gates, telemetry, and scoring. Use when running or improving task-spec-driven delegation workflows.
luanmorenommaciel/kimi-plugin-cc
Plugin Claude Code
Bundles 2 skills, 12 commands, 1 agent · 309 tokens together
Use Kimi from Claude Code to review code, explore codebases, or delegate tasks.
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: