A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Written for a practitioner: someone who already uses Claude Code and wants to know what these plugins do and whether to install them. If you are new to Claude Code, start with the official docs. For the design rationale behind a plugin, see the book.
Requires Claude Code 2.1.16+ and Python 3.9+ for hooks.
# Add the marketplace, then install the plugins you want
/plugin marketplace add athola/claude-night-market
/plugin install sanctum@claude-night-market # Git workflows
/plugin install pensive@claude-night-market # Code review
/plugin install spec-kit@claude-night-market # Spec-driven devRun claude --init once after installing. Two other paths
exist: npx skills pulls the skill files alone
into .claude/skills/, without commands, agents, or hooks, and
opkg i gh@athola/claude-night-market --plugins sanctum,pensive
installs whole plugins from the openpackage.yml each one ships.
Full options are in the
Installation Guide.
If the
Skilltool is unavailable, read skill files directly atplugins/{plugin}/skills/{skill-name}/SKILL.md.
Night Market is built around the loop you already work in. A typical feature runs end to end on a handful of commands:
- Start a feature.
/attune:missionroutes you through brainstorm, specify, plan, and execute phases. - Write the code.
imbueenforces a failing test first, so the test is written before the implementation. - Review before you push.
/full-reviewruns a multi-discipline pass;/refine-codecleans up duplication and dead code. - Ship it.
/prepare-prruns quality gates and drafts a description that says who the change is for, where it lands inside and outside the codebase, and when it is fully integrated. - Pick up where you left off.
/catchuprebuilds context from recent git history after a break.
The commands you reach for most:
| Task | Command |
|---|---|
| Run the project lifecycle | /attune:mission |
| Initialize a new project | /attune:arch-init |
| Review a PR | /full-review |
| Address review feedback | /fix-pr |
| Implement an issue | /do-issue |
| Prepare a pull request | /prepare-pr |
| Write a spec | /speckit-specify |
| Catch up on changes | /catchup |
| Package project knowledge as skills | /attune:skill-library |
| Clean up the codebase | /unbloat |
| Pressure-test a decision | /attune:war-room |
Full task-by-task walkthroughs are in the Common Workflows Guide.
23 plugins in four layers. Each installs independently, and dependencies pull their shared runtime automatically.
Foundation is the base every other layer builds on:
leyline (auth, quotas, error patterns, trust verification),
sanctum (git, commits, PR prep, sessions), and imbue
(TDD enforcement, proof-of-work, scope guarding).
Utility handles cross-cutting concerns: conserve (context
and token optimization), conjure (delegation to seven external
model CLIs plus a local runner), hookify (a behavioral rules
engine with a security catalog), egregore (autonomous agent
orchestration), herald (notifications), and oracle (local ML
inference).
Domain is where the day-to-day work happens: pensive (code
and architecture review), attune (project lifecycle), spec-kit
(spec-driven development), parseltongue (Python), minister
(GitHub issues and DORA metrics), memory-palace (knowledge
organization), archetypes (architecture paradigms), gauntlet
(codebase learning), phantom (computer use), scribe
(documentation and slop detection), scry (recordings), tome
(research), and cartograph (codebase visualization).
Meta improves the system itself: abstract (skill authoring,
hook development, evaluation, and skill-stability tracking).
The full skill, command, and agent inventory is in the Capabilities Reference.
⚠️ Plugins run inside your Claude Code session and can read or edit your repo, run shell commands, and call external services. Review any plugin before installing it.
Three guards reduce the blast radius, but none replace your own review:
- TDD gates (
imbue) block implementation writes that lack a failing test. - Destructive-command blockers (
conserve,hookify) auto-approve safe commands and halt or warn onrm -rf,git push --force, and production-shaped targets. - Additive-bias audits (
leyline) flag unjustified additions before commit.
CONSTITUTION.md holds the immutable rules that override any conflicting skill or hook; STEWARDSHIP.md is the maintenance contract.
Three parts of the marketplace reach off your machine. Each can be turned off.
Two hooks use your existing GitHub credentials, and both fail
silently when gh is unauthenticated or the network is
unavailable.
- Star prompt (
leyline,plugins/leyline/hooks/auto-star-repo.sh). On session start it checks whether you have starredathola/claude-night-market, using yourghCLI auth or aGITHUB_TOKEN/GH_TOKENenv var. It only reads star status and asks once per session; it never stars or unstars without your consent. Opt out by settingCLAUDE_NIGHT_MARKET_NO_STAR_PROMPT=1. - Learnings and insights posting (
abstract,plugins/abstract/hooks/post_learnings_stop.py). On session stop, if~/.claude/skills/LEARNINGS.mdhas content, it posts a skill-usage summary (and may promote high-severity items to issues) via your authenticatedghCLI. The target is detected at runtime: atarget_repooverride in~/.claude/skills/discussions/config.json, otherwise the current repo fromgh repo view. Posting defaults to on; opt out by settingauto_post_learningstofalsein that config file.
The third sends the contents of your files. Delegation
(conjure, also reached by attune missions and egregore
pipeline steps) hands execution work to whichever external model
CLI answers first, in the order Gemini, Qwen, MiniMax, GLM, Muse,
Codex, OpenCode. The prompt and the file contents it carries go to
that provider, under the credentials you configured for it. This
runs by default. Decline it for one run with
CONJURE_DELEGATION=off, or for one machine by setting
"enabled": false in
~/.claude/hooks/delegation/config.json. When no provider
answers, the work stays on your machine.
- Claude Code 2.1.16+ (2.1.32+ for agent teams, 2.1.38+ for security features).
- Python 3.9+ for hooks (macOS ships 3.9.6). Hook code must
stay 3.9-compatible; plugin packages may target 3.10+ via
virtual environments. Working on this repo itself needs
Python 3.12+, which the root
pyproject.tomlpins. See the Plugin Development Guide for the rules. - GNU make 3.82+ to build this repo. The Xcode command line
tools ship 3.81, which runs the recipes without the flags they
rely on.
makewarns once per invocation when it detects this. On macOS:brew install make, then rungmake.
make validate-all
make lint && make test # checks only; rewrites nothing
make fix # ruff format + ruff check --fixA plugin directory holds .claude-plugin/plugin.json (metadata)
plus any of commands/, skills/, hooks/, agents/,
workflows/, and tests/, with a Makefile and
pyproject.toml. A workflows/ script orchestrates several
subagents at once and runs only when you ask for one. Copy the
layout from an existing plugin such as plugins/abstract, then
see the Plugin Development Guide for structure and
naming conventions.
- Installation Guide
- Quick Start
- Common Workflows
- Plugin Development Guide
- Capabilities Reference
- Tutorials
- Architecture Decision Records
- CHANGELOG
Per-plugin pages are in book/src/plugins/.
Every plugin is entrusted to the community: steward rather than
own, and think several iterations ahead. Each plugin maintains
its own tests and docs; run make test at the repo root to
execute every suite, and /stewardship-health to view per-plugin
health. Contribution guidelines are in the
Plugin Development Guide.
Night Market builds on Anthropic Claude Code and integrates with github/spec-kit (v0.5.0) and obra/superpowers (v5.0.7, see the integration guide). Its AI involvement is declared under the Quillx disclosure standard as 3/5 (Adapted): human-directed, AI-generated, and meaningfully edited.