Your AI writes fast.
Temper makes it last.
IDD + BDD + TDD for AI-generated code. Quality gates, blast radius analysis, and intent-driven development. The AI discipline layer for Claude Code and Cursor.
IDD + BDD + TDD for AI-generated code. Quality gates, blast radius analysis, and intent-driven development. The AI discipline layer for Claude Code and Cursor.
/plugin marketplace add galando/temper /plugin install temper
Commands available in any project.
bash <(curl -fsSL https://raw.githubusercontent.com/galando/temper/main/scripts/install-cursor.sh)
Full feature parity with Claude Code.
All features from v4.0 through v4.4.1 — feedback loops with circuit breakers, Cursor IDE support with feature parity, a three-tier pack system with linking, and honest documentation.
Review finds issues? Gate shows "Loop back to Build". Check fails tests? Targeted fix task. Build discovers bad plan? Loop back to Plan. Circuit breaker: max 2 loops, same issue twice = stop.
Full Temper for Cursor. Generation script mirrors .claude/ to .cursor/. Commands, skills, packs — all adapted.
Three-tier resolution (project > global > built-in), plugin/skill linking, phase scoping, cached manifests, quick-create launchers. Packs are a first-class extensibility layer.
Each stage writes structured context for downstream stages. No more "agent amnesia" — Review knows what Build struggled with, Check knows what Review already fixed.
System architecture, API contracts, DB schema, integration points, and decision logs. Auto-skipped for simple features.
Plan and Design walkthroughs link to each other at their final gates. Skip to build from any section. Non-linear exploration.
Per-stage metrics: tokens, latency, tool calls. Tracked in /temper:status. Config reference, not aspirational numbers.
Observability shows config, not fake numbers. Adaptive Learning marked as planned. All version strings and install commands verified.
v3.1.0 makes Temper's analysis real. Instead of reading tests and judging quality, Temper now runs your tests and shows you the proof.
Every Gherkin scenario in intent.md gets executed individually against your test runner. Real pass/fail, real output, real execution time. Not Claude's opinion — proof.
Optional MCP servers upgrade heuristic analysis to proven findings. code-review-graph for blast radius and call chains, semgrep for SAST scanning.
Every finding carries a label: [PROVEN] (tool output), [HEURISTIC] (grep-based), or [SEMANTIC] (interpretation). You know exactly what's verified.
No MCP servers? Everything works exactly as v3.0.0. Progressive enhancement, zero breaking changes.
See full changelog on GitHubMost AI tools only answer "does the code work?" Temper answers all three questions that matter.
Did we solve the problem? Success criteria with structured validation types. Not just "tests pass" — the feature actually addresses the need.
Does it do the right things? Scenarios derived BEFORE architecture. Every file traces to a behavior. No over-engineering.
Does the code work? Tests written from scenarios. RED → GREEN → REFACTOR. Scenario coverage gate ensures nothing is missed.
All three layers live in a single markdown artifact. Problem, scenarios, and coverage checklist in one place.
Temper doesn't just generate code — it plans, validates, tests, and learns. Every step is verified before moving forward.
Understands impact before coding. Maps affected files, dependencies, and risk areas.
Auto-generates flowcharts, sequence diagrams, and state machines. See the plan visually before building.
Walk through the plan section by section — intent, scenarios, architecture, blast radius, tasks — with Q&A at each step.
Tests must pass. Coverage must be met. The AI cannot proceed until verified.
Four steps from idea to production-ready code. Temper automates quality — you focus on shipping.
/temperOne command starts it all. Temper analyzes blast radius, generates mermaid architecture diagrams, creates BDD scenarios, and presents an interactive plan. Walk through step by step or approve and build.
Temper implements automatically with TDD gates enforced at every step. Tests written first, code follows. Stage gate asks to continue.
Temper reviews automatically against enabled packs. Findings scored by confidence. Stage gate confirms all checks passed.
Temper commits your changes with a proper message. Branch ready to push. Use /temper:status anytime to track quality metrics.
Future releases will make Temper smarter over time — learning your patterns and suggesting improvements. Review memory already persists between sessions.
Identifies recurring issues and anti-patterns in your code.
Proposes new rules based on what it learns from your reviews.
Suppresses false positives as it learns your codebase patterns.
Rules that enforce best practices. Each pack has BLOCK, WARN, and SUGGEST severity levels.
Add a rules.md file and Temper will automatically discover it. Three-tier resolution: project > global > built-in. Link packs to plugins or skills for automatic context injection.
.claude/packs/my-company/rules.md
# My Company Standards
## BLOCK
- All API responses use DTOs
- No raw SQL queries
## WARN
- Constructor injection only
- Max method length: 20 lines
Type /temper:pack in any project
Temper scans your codebase and asks about patterns it finds
Temper generates a custom rules.md based on your answers
One command runs the full SDLC: plan → design → build → review → check with stage gates, feedback loops, and observability.
/temper "add login feature" # Full SDLC in one command
Runs plan, build, review, and check with interactive stage gates. Each stage asks for confirmation before proceeding.
For granular control, use individual commands.
Plan with blast radius, mermaid diagrams, and interactive walkthrough
System design for complex features (auto-skipped for simple)
Build with TDD + quality gates
Review with confidence scoring
Stack validation (auto-detect)
Root cause analysis + fix
Manage quality packs
Quality metrics dashboard
Unified: plan → design → build → review → check
Auto-detection with zero configuration.
/plugin marketplace add galando/temper /plugin install temper
Commands are now available in any project. For optional MCP-powered analysis, see Recommended Setup.
bash <(curl -fsSL https://raw.githubusercontent.com/galando/temper/main/scripts/install-cursor.sh)
Mirrors .claude/ to .cursor/ — commands, skills, packs, and reference docs. Full feature parity.