2,279 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Full feature-development pipeline for this repo — isolated worktree, spec, implementation plan, TDD build, quality gates, then a review→fix loop that only stops when review passes. Each stage delegates to a named project subagent (spec-researcher, pattern-scout, pipeline-implementer, pipeline-simplifier…
This rule outlines the strict Test-Driven Development process to be followed by the AI assistant when implementing new features or fixing bugs. This complements the broader developmentworkflow by providing specific TDD execution steps for the AI.
Use 901 to run one feature end-to-end through SpecFlow's full pipeline as a single git-tracked run: high-level design, happy-path specs, scenario-by-scenario test-driven build-out validated and committed per module, cleanup, an optional expanded-coverage round, and a merge back to the base branch. Every design/spec…
This sop guides the implementation of code tasks using test-driven development principles, following a structured Explore, Plan, Code, Commit workflow. It balances automation with user collaboration while adhering to existing package patterns and prioritizing readability and extensibility. The agent acts as a…
Turn AI software engineering into an auditable, on-disk state machine. A staged PDLC workflow (PRD, design, TDD, implement, review, ship, retro) enforces hard contracts — artifacts on disk, per-feature state machine, tests-before-code, objective checks from real command exit codes, single-shot auto-repair — so AI work.
★not rated 11▲
+1 25d agoA
tokens not measured
originalMIT
A three-stage workflow for turning an idea into tested code: explore the requirements, write an implementation plan, then repeatedly build, test, and commit the changes.
Production-quality Elixir development with enforced precommit gates, TDD workflows, and escalation-based patterns for OTP, Phoenix LiveView, and distributed systems.
Instructions for strelov1/spec-driven-tdd: This repo is a skill-pack. When implementing an OpenSpec change, invoke the spec-driven-tdd skill and follow its lifecycle: plan in OpenSpec, isolate in a worktree, implement each task via TDD → simplify → review, then finish + archive.
Apply or continue an SDD change with orchestrated BDD/TDD implementation, verification, artifact reconciliation, reverse traceability, self-check, and bounded subagents. In default/full mode, persist through every safe implementation and remediation slice until the Change is implementation-complete, transitioned to…
Interview the user about what a loop harness should accomplish, then generate KEYOBJECTIVE, verifyobjective(), prompt functions, and the verify() gate directly into loop.sh. Use when the user wants to configure a new loop task, or says "looprinter-interview", "new loop", or "loop interview".
Claude Code instructions for changh95/vram-calculator, covering vram calculator, stack & commands, architecture rules, math & data integrity (the product's credibility) and tdd — non-negotiable.
TDD-first spec management for AI coding workflows. Use this skill when the user explicitly mentions specs, forging, or structured planning: says "forge", "forge a spec", "write a spec for X", "create a spec", "plan X as a spec", "resume", "what was I working on", "spec list/status/pause/switch/activate", "implement…
Instructions for kirkchen/beat, covering claude.md, what is beat, installation, architecture and plugin structure.
★not rated 7 2mo agoA3,899 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: