Your AI writes fast.
Temper makes it last.

An intent-gated SDLC for AI-generated code. Every gate verdict is computed by a small auditable CLI from an evidence ledger — never asserted by a model — and a red gate physically blocks git commit.

Temper Dashboard
/plugin marketplace add galando/temper
/plugin install temper

That’s the whole install. Your first /temper "…" sets the project up — config, scaffold, and the commit gate.

The Loop

One pipeline, a human gate at every stage

INTENT → PLAN → DESIGN? → BUILD → REVIEW → CHECK → COMMIT

Intent Gate First

You approve the Problem and success criteria before any exploration or architecture spends tokens. A wrong intent multiplies into wrong everything — correcting it here costs words; after Plan it costs the plan.

Deterministic Gates

Each stage’s PASS/FAIL is computed by temper gate from an evidence ledger of real commands and exit codes. A red gate blocks git commit via a native pre-commit hook; a human override is recorded with their identity, never erased.

Scenarios Before Architecture

BDD scenarios are derived from a measured blast radius, so every planned file traces to a behavior — the structural defense against over-engineering.

The Loop Closes Itself

temper bands watches metric history with control bands (pure arithmetic, no model); a breach is drafted as the next intent and rides the same gates. Fixes write a committed lessons file every future investigation reads first.

Versioned quality packs (security, TDD, quality, performance…) enforce policy during build and review, with deterministic hook backstops. Works with any CI — the automation surface is commands and exit codes, no platform files.  Temper vs the AI-native SDLC playbook →

Evidence

Does It Actually Catch Bugs?

Architecture arguments are fine. Results are better. Three seeded-defect projects run through the live pipeline in CI — a gate must mechanically FAIL naming the defect.

Missing Rate Limiting

AI built password reset. All tests pass. The scenario coverage gate caught the gap: no test for rate limiting. Build wrote the test → failed → implemented it → passed.

Over-Engineering

AI planned 3 classes for a single validation rule. File-to-scenario traceability flagged it: one scenario, one function needed. Three files became zero.

Wrong Problem Solved

AI built the feature correctly — plus an admin-only endpoint nobody asked for. Untraced file flagged and removed before commit.

Claims here are measured, not asserted — including the unflattering ones: the v8 prompt rewrite cut a Plan run’s cost 48% and held quality, but did not make it faster, and the changelog says so.

See all evidence →  ·  Self-eval methodology

Methodology

IDD + BDD + TDD: Three Layers, One File

Most AI tools only answer “does the code work?” Temper answers all three questions that matter.

IDD — Intent-Driven

Did we solve the problem? Success criteria with structured validation types, accepted by a human at the intent gate before anything is built.

BDD — Behavior-Driven

Does it do the right things? Scenarios derived before architecture. Every file traces to a behavior.

TDD — Test-Driven

Does the code work? Tests written from scenarios, RED → GREEN evidence the build gate requires. The coverage gate ensures nothing is missed.

One File: intent.md

All three layers live in a single committed artifact — problem, scenarios, coverage checklist — and the chain of commits is the audit trail.

Commands

Three commands you’ll actually type

/temper runs and routes everything else.

🔥

/temper "add password reset"

The whole pipeline, intent gate to commit — or arm autonomy at the plan gate and it runs unattended, parking before commit

🔧

/temper:fix "500 on checkout"

Root cause → failing test (write-protected) → minimal fix → validated

💡

/temper:intent "an idea"

Capture an idea as a committed draft — from anyone — and build it later

Granular control: :plan :design :build :review :check :status :pack  — full reference →

Install

Two steps

/plugin marketplace add galando/temper
/plugin install temper

Then just use it — the first /temper in a project bootstraps config, scaffold, and the native commit gate. Auto-detects Spring Boot, React+TS, Node/Express, FastAPI, Go, and Rust. Optional MCP-powered analysis: Recommended Setup.