Skip to content

galando/temper

Repository files navigation

Temper

Your AI writes fast. Temper makes it last.

Quality gates, blast radius analysis, and intent-driven development for AI-generated code

Version License: MIT Claude Code Plugin DeepWiki

Website · Getting Started · Releases

Quick Start: /plugin marketplace add galando/temper then /temper "add password reset" — one command for the full pipeline.

Headless / CI (claude -p): use the fully-qualified name, /temper:temper "..." — the bare /temper alias only resolves in an interactive session.

The Problem

AI writes code fast. But "fast" without "right" creates bugs, technical debt, and features that miss the point. AI-generated code has structural failure patterns:

Pattern What Goes Wrong
Missing behaviors Happy path works, edge cases never implemented
Wrong problem solved Feature works perfectly, but nobody asked for it
Over-engineering Factories and strategies for something used once
Hallucinated APIs Methods called that don't exist
Missing wiring Code correct, integration missing

Most AI tools check if code compiles. Temper checks if it solves the right problem, handles edge cases, and is safe to ship.

The Catch

The rate-limiting bug that vanilla AI always misses:

Scenario: Rate limiting on reset requests
  Given a user has requested 3 resets in 10 minutes
  When they request another reset
  Then the request is rejected with 429

AI built password reset. All tests pass. But Temper's scenario coverage gate caught the gap: no test for rate limiting. Build wrote the test. Test failed. Build implemented rate limiting. Test passed. Without the coverage gate, rate limiting would never have been implemented.

More: Evidence Gallery

How It Works

Three methodologies, one contract file (intent.md):

intent.md
|
+-- Intent (IDD)           WHY are we building this?
|   Problem, success criteria, constraints
|
+-- Scenarios (BDD)        WHAT should it do?
|   Gherkin Given/When/Then, derived BEFORE architecture
|
+-- /temper:build (TDD)    HOW do we build it?
    Tests from scenarios, RED → GREEN → REFACTOR

Key insight: Scenarios are derived before architecture. The file plan follows from what the system must do, not the other way around. This prevents over-engineering structurally.

Full methodology: docs/methodology.md

Autonomous Continuation (opt-in) (v6.0.0)

After you approve the plan, /temper can run the remaining stages (design → build → review → check → eval) unattended and leave a report. It never pushes or merges, never re-plans on its own, and parks before commit and on anything needing a human. Turn it off and Temper behaves exactly as before.

First run: pre-allow your build/test commands in settings.json, or the run parks on the first unpermitted command. No config yet? /temper:init seeds one. Details: docs/proposals/autonomous-mode.md

Token Efficiency (v5.9.0)

Temper cuts a run's token cost with three optimizations — all ON by default, all revert to v5.8.0 when their flag is off:

Optimization Default Quality tradeoff
Cache static methodology reads on None — same reads, ~90% off re-read cost
Adaptive depth — size the pipeline to the change on (floor: simple) Only one with a tradeoff — see below
Incremental loops — inline auto-fix, no subprocess on (inline-threshold: 3) None for auto-fixable findings

The one decision you make: adaptive-depth runs a lighter pipeline on small changes. It's safe when the change is genuinely isolated — but if it touches a shared interface, auth, money, or has an unclear blast radius, click "Escalate to full pipeline" at the plan gate (one click, that change only — no config editing). For a whole high-stakes codebase, set floor: medium in .claude/temper.config once and never think about it again.

Full explanation (mechanism, tiers, decision rule, when quality drops): docs/token-efficiency.md

Commands

Command Purpose
/temper Full pipeline: plan → design? → build → review → check
/temper:plan Blast radius + BDD scenarios + architecture
/temper:design System design (complex/medium features)
/temper:build Scenario-driven TDD + coverage gate
/temper:review Intent validation + confidence scoring
/temper:check Stack-aware validation pipeline
/temper:fix Root cause analysis + regression test
/temper:pack Manage quality packs
/temper:status Quality metrics + observability dashboard

Quality Packs

Rule sets enforced during code generation and review. Three-tier resolution: project-local → global → built-in.

Pack What It Enforces
quality Method length, DRY, naming, complexity
tdd RED-GREEN-REFACTOR, coverage
security OWASP Top 10, no secrets in code
performance N+1 detection, pagination, Core Web Vitals
api-design Additive extension, idempotency, consistent naming
architecture-depth Module depth: seams, adapters, locality, leverage

Create custom packs with /temper:pack or add a rules.md to .claude/packs/your-pack/.

Security & Trust

Temper is Markdown all the way down — every command, skill, and pack is an auditable prompt file in this repository. The trust contract:

  • No network calls, no telemetry. Temper never phones home. The only shell commands it runs are your project's own build/test/lint commands, and only under Claude Code's normal permission prompts.
  • Writes are confined to your project. Temper writes .claude/temper.config (created by /temper:init, only with your approval) and its working files under .temper/ in your project. It never touches files outside the project directory.
  • Autonomous Continuation is opt-in and fenced. It is armed per-run at the plan gate, never at invocation. It never commits, never pushes, never merges — it parks before commit and leaves a report. With the autonomy: config absent, behavior is byte-identical to non-autonomous Temper.
  • Optional MCP servers are optional. The recommended servers below only upgrade evidence quality; nothing breaks without them.

Installation

Claude Code

/plugin marketplace add galando/temper
/plugin install temper

Cursor IDE

# Into a Temper repo checkout (regenerates .cursor/ from plugin sources):
./scripts/install-cursor.sh

# Into an arbitrary project (downloads a static snapshot):
bash <(curl -fsSL https://raw.githubusercontent.com/galando/temper/main/scripts/install-cursor.sh)

Cursor support is frozen at the v5.1 feature set (CHANGELOG v5.2.1 platform strategy). New capabilities ship Claude Code-first. The .cursor/ export is regenerated from plugin sources on every release via scripts/generate-cursor.sh — parity is honest and consistent, not stale-by-accident. Running install-cursor.sh inside a repo checkout delegates to the generator (offline, idempotent). The .cursor/ directory is a derived, self-contained export: Claude Code ignores it entirely, and it is not part of the plugin's command/skill surface.

Recommended Setup

Temper works out of the box. Two optional MCP servers upgrade heuristic analysis to mechanically verified findings:

Server Provides Install
code-review-graph AST-level dependency graphs, call chains, impact radius pip install code-review-graph
semgrep SAST scanning, security vulnerabilities brew install semgrep
open-code-review External LLM-powered defect detection (Alibaba) npm install -g @alibaba-group/open-code-review
# Register with Claude Code (requires restart)
claude mcp add code-review-graph -- code-review-graph
claude mcp add semgrep -- semgrep --mcp

Every finding carries an evidence label: [PROVEN] (tool-verified), [HEURISTIC] (grep-based), [SEMANTIC] (judgment), [OCR] (external engine).

Full setup: docs/recommended-setup.md

Supported Stacks

Stack Detection Auto-Commands
Spring Boot pom.xml / build.gradle mvn compile, mvn test
React + TS package.json + tsconfig.json npm test, npm run build
Node/Express package.json + express npm test, npm run lint
FastAPI pyproject.toml + fastapi pytest, ruff check
Go go.mod go test, golangci-lint
Rust Cargo.toml cargo test, cargo clippy

Documentation

Contributing

See CONTRIBUTING.md for guidelines.

License

MIT (c) Gal Naor


Back to Top

Made with care for the AI coding community

About

Temper is a plugin for Claude Code & Cursor that closes the quality gap in AI-generated code

Resources

License

Contributing

Stars

13 stars

Watchers

0 watching

Forks

Packages

 
 
 

Contributors