By nightgauge
AI-Augmented SDLC Framework - Complete issue-to-PR pipeline with enforceable quality gates
Reference for Nightgauge' own surfaces — the `nightgauge forge` abstraction, the `nightgauge` Go binary subcommands, and the @nightgauge/sdk API — with the gotchas that bite when you use them. Use when authoring or editing a skill, plugin command, automation, or script that shells out to `nightgauge`/`forge` or imports the SDK, or whenever you are about to reach for a bare `gh`/`glab` call and need the forge equivalent.
Display the effective Nightgauge configuration with source annotations, showing where each value comes from (default, global, project, or environment). Use when debugging config precedence or confirming which tier supplies a value.
Re-review the current change with fresh-eyes critics that have no authoring context, each attacking it from a distinct lens (correctness, security, reuse/simplification, tests), then drive a fix loop until findings degrade to nitpicks. Use to harden a diff before opening or merging a PR, when asked for an adversarial/critical review, or from feature-dev/pr-create as an optional hardening gate.
Analyze an epic's sub-issues and recommend batch vs sequential pipeline processing strategy. Use before starting work on an epic to determine optimal execution approach.
Perform periodic backlog triage - identify stale issues, detect duplicates, validate priorities, and discover dependencies. Use weekly/monthly for backlog hygiene.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
![]()
AI-powered Issue-to-PR pipeline with enforced quality gates.
Nightgauge transforms how teams build software by guiding AI agents through a structured development workflow—from issue creation to merged pull request. Every step enforces documentation-first practices, acceptance criteria validation, and automated quality checks.
Everything in this repository is Apache-2.0 licensed. The VS Code extension, SDK, portable skills, Claude plugin, and Go binary run locally using model and forge credentials you control. No Nightgauge account or hosted service is required, cloud connectivity is disabled by default, and telemetry is opt-in.
Optional services may integrate through public contracts, but their private implementations and commercial plans are outside this repository. See VISION.md and docs/PRODUCT_OVERVIEW.md.
Have these in place before installing — the pipeline orchestrates tools you already use rather than replacing them:
| Requirement | Needed for |
|---|---|
| Claude Code (or another supported adapter) | Stage execution — bring your own subscription/keys; nothing is proxied |
| git + gh CLI (authenticated) | Branching, PRs, issue operations |
| A GitHub repository with issues | The pipeline's unit of work |
GitHub Projects v2 board (+ .nightgauge/config.yaml pointing at it) | The autonomous scheduler and board-driven views — without a board you can still run single issues manually |
Node.js ≥ 24 (pinned in .nvmrc) | VSCode extension and SDK builds |
Platform support: macOS is the primary end-to-end tested platform. Packaged Linux amd64 CLI and VSIX binaries are tested on Debian and Alpine; live provider-driven Linux pipelines still have less coverage. Windows is not currently supported; use WSL2.
git clone https://github.com/nightgauge/nightgauge.git
cd nightgauge
go install ./cmd/nightgauge
Signed release binaries, checksums, and the Homebrew cask will be available with the first public release. Until then, build from the reviewed source tree. See docs/GO_BINARY.md for the full install matrix and details on each method.
The full Nightgauge experience with visual dashboard, project board integration, batch processing, and one-click pipeline execution.
Before the first production release, use a target-specific VSIX from a reviewed
GitHub Actions release-candidate run. After v0.2.0, download the VSIX matching
your OS/architecture from the GitHub Release and install it with Extensions →
… → Install from VSIX. Building locally or running dev-install.sh is for
extension development and intentionally produces a non-release build.
Not yet on the VS Code Marketplace — a Marketplace listing is planned as its own follow-up release.
Features:
For terminal-based workflows, install the Nightgauge plugin:
# Add the marketplace
claude plugin marketplace add https://github.com/nightgauge/nightgauge.git
# Install the Nightgauge plugin
claude plugin install nightgauge@nightgauge-plugins
# Start the pipeline
/nightgauge:issue-pickup
Codex support is available through both slash commands and the unified stage runner.
Install Codex assets (commands + skills):
./scripts/install-agent-skills.sh --codex-only
Slash commands are defined in .codex/commands/ and invoked as /<name>:
npx claudepluginhub nightgauge/nightgauge --plugin nightgaugeComplete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.