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.
Write a skill once, use it everywhere. Skrills validates and syncs skills, commands, agents, MCP servers, and hooks across **Claude Code, Codex CLI, GitHub Copilot CLI, and Cursor**, all from a single Rust binary. Install · User Guide · CLI Reference · FAQ ·
@atholaFAQ
claude-night-market is a Claude Code plugin with 200 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes claude-code-plugin-reference, night-market-architecture-contract, night-market-build-and-env. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
> /plugin marketplace add athola/claude-night-market
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.
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 dev
Run claude --init once after installing. Prefer one command?
npx skills add athola/claude-night-market installs everything;
opkg i gh@athola/claude-night-market --plugins sanctum,pensive
installs a subset. 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:
/attune:mission routes you through
brainstorm, specify, plan, and execute phases.imbue enforces a failing test first,
so implementation follows the test, not the other way around./full-review runs a
multi-discipline pass; /refine-code cleans up duplication
and dead code./prepare-pr runs quality gates and leaves a
clean git state ready for a pull request./catchup rebuilds 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 Gemini and
Qwen), 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:
imbue) block implementation writes that lack a
failing test.conserve, hookify)
auto-approve safe commands and halt or warn on rm -rf,
git push --force, and production-shaped targets.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.
Two hooks reach the network using your existing GitHub credentials.
Both fail silently when gh is unauthenticated or the network is
unavailable, and both can be turned off.
leyline,
plugins/leyline/hooks/auto-star-repo.sh). On session start it
checks whether you have starred athola/claude-night-market,
using your gh CLI auth or a GITHUB_TOKEN / GH_TOKEN env
var. It only reads star status and asks once per session; it
never stars or unstars without your consent. Opt out by setting
CLAUDE_NIGHT_MARKET_NO_STAR_PROMPT=1.abstract,
plugins/abstract/hooks/post_learnings_stop.py). On session
stop, if ~/.claude/skills/LEARNINGS.md has content, it posts a
skill-usage summary (and may promote high-severity items to
issues) via your authenticated gh CLI. The target is detected
at runtime: a target_repo override in
~/.claude/skills/discussions/config.json, otherwise the
current repo from gh repo view. Posting defaults to on; opt
out by setting auto_post_learnings to false in that config
file.1.9.17 upgrades tome from a multi-channel search tool into a
research engine. It keeps the citation edges it already fetched and
previously discarded, links them into memory-palace's knowledge graph,
and serves that graph back as research threads (community detection),
suggested next connections (link prediction), and semantic retrieval
ranked by embedding similarity. memory-palace is an optional
co-installed backend: when it is absent, tome raises an explicit
capability error rather than degrading silently. A new offline metrics
harness (make metrics) scores retrieval quality (nDCG, MRR, recall),
source diversity, and citation impact against a committed gold set with
no network or model access.
memory-palace also drained its capture backlog. The 196 inert pending
captures (41% of the index) were promoted into the active corpus, and
the SessionStart surfacer now names the top promoted captures.
The release also restores Python 3.9 support across all 23 plugins.
Every pyproject.toml pins requires-python = ">=3.9", the uv.lock
files were refreshed, and ruff targets py39 so hooks stop suggesting
3.10+ idioms on code that ships to 3.9 users. See the
CHANGELOG for the full history.
make create-plugin NAME=my-plugin
make validate
make lint && make test
A plugin directory holds .claude-plugin/plugin.json (metadata)
plus any of commands/, skills/, hooks/, agents/, and
tests/, with a Makefile and pyproject.toml. See the
Plugin Development Guide for structure and naming
conventions.
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 live in the
Plugin Development Guide.
Night Market builds on Anthropic Claude Code and
integrates with github/spec-kit (v0.5.0),
obra/superpowers (v5.0.7, see the
integration guide), and three patterns adapted
from QAInsights/Quillx. Per-plugin attributions are in
each plugin's pyproject.toml.
.cclsp.json
.claude/
.claude-plugin/
marketplace.json
agents/
code-review-mode.md
documentation-mode.md
plugin-developer.md
context_governance.json
quality_gates.json
rules/
bounded-discovery.md
ceremony-requires-need.md
markdown-formatting.md
plan-before-large-dispatch.md
prefer-invariants-over-fallbacks.md
prefer-rg-over-grep.md
shared-utility-consumer-rule.md
skill-exit-criteria.md
slop-scan-for-docs.md
settings.json
skills/
claude-code-plugin-reference/
SKILL.md
night-market-architecture-contract/
SKILL.md
night-market-build-and-env/
SKILL.md
night-market-change-control/
SKILL.md
night-market-collective-memory/
SKILL.md
night-market-completion-integrity-campaign/
SKILL.md
night-market-config-catalog/
SKILL.md
night-market-debugging-playbook/
SKILL.md
night-market-diagnostics-toolkit/
scripts/
health-snapshot.sh
SKILL.md
night-market-docs-and-writing/
SKILL.md
night-market-failure-archaeology/
SKILL.md
night-market-operations/
SKILL.md
night-market-research-frontier/
SKILL.md
night-market-research-methodology/
SKILL.md
night-market-validation-and-qa/
SKILL.md
.feature-review.yaml
.github/
DISCUSSION_TEMPLATE/
decisions.yml
deliberations.yml
insights.yml
knowledge.yml
learnings.yml
ISSUE_TEMPLATE/
issue-template.md
projects/
initiatives-project-config.json
workflows/
capabilities-sync.yml
cron-memory-palace.yaml
cross-framework-publish.yml
deploy-book.yml
ecosystem-tests.yml
mutation-testing.yml
python39-compat.yml
security.yml
slop-check.yml
tome-integration.yml
trust-attestation.yml
typecheck.yml
.gitignore
.linkcheckignore
.mcp.json
.pre-commit-config.yaml
.pre-commit-hooks.yaml
assets/
architecture-dark.svg
architecture-light.svg
architecture.d2
gifs/
skills-showcase.gif
tapes/
add-subtitles.sh
README.md
skills-showcase.manifest.yaml
skills-showcase.tape
validate-and-regenerate.sh
book/
book.toml
src/
achievements/
README.md
getting-started/
common-workflows.md
first-plugin.md
installation.md
migration-guide.md
quick-start.md
README.md
introduction.md
plugins/
abstract.md
archetypes.md
attune.md
cartograph.md
conjure.md
conserve.md
domain-specialists.md
egregore.md
foundation-layer.md
gauntlet.md
herald.md
hookify.md
imbue.md
leyline.md
memory-palace.md
meta-layer.md
minister.md
oracle.md
parseltongue.md
pensive.md
phantom.md
README.md
sanctum.md
scribe.md
scry.md
spec-kit.md
tome.md
utility-layer.md
reference/
capabilities-agents.md
capabilities-commands-extended.md
capabilities-commands.md
capabilities-hooks.md
capabilities-reference-details.md
capabilities-reference.md
capabilities-skills.md
capabilities-workflows.md
function-extraction-guidelines.md
superpowers-integration.md
SUMMARY.md
tutorials/
code-review-pr-workflow.md
debugging-issues.md
feature-lifecycle.md
memory-palace-knowledge.md
README.md
skills-showcase.md
theme/
css/
gamification.css
js/
achievements.js
mermaid-init.js
bridge/
openclaw/
openclaw.plugin.json
README.md
CHANGELOG.md
conftest.py
CONSTITUTION.md
docs/
adr/
0001-plugin-dependency-isolation.md
0002-quota-tracker-refactoring.md
0003-command-description-refactoring.md
0004-skill-description-budget-optimization.md
0005-attune-discoverability-enhancement.md
0006-self-adapting-skill-health.md
0007-github-discussions-integration.md
0008-behavioral-contract-verification.md
0009-sidecar-service-discovery.md
0010-stacked-diff-workflows.md
0011-session-capture-envelope.md
0012-confidence-tagged-claims.md
0013-naur-theory-building.md
0014-pensive-review-skill-consolidation.md
0015-orchestrator-skill-simplification.md
0016-orphan-skill-decisions.md
0017-confidence-and-theory-building-decisions.md
0018-tome-graph-reuse-over-build.md
0019-superpowers-design-consolidation.md
agent-model-matrix.md
api-overview.md
dependency-audit.md
error-handling-template.md
examples/
async-web-scraper-demo.md
context-optimization-demo.md
hook-development/
hook-types-comprehensive.md
security-patterns.md
makefile-testing/
comprehensive-examples.md
README.md
skill-development/
authoring-best-practices.md
evaluation-methodology.md
graphviz-examples.md
guides/
agent-boundaries.md
authentication-integration.md
data-extraction-pattern.md
development-vs-runtime-skills-separation.md
documentation-standards.md
error-handling-guide.md
lsp-native-support.md
plugin-dependency-pattern.md
README.md
skill-observability-guide.md
skills-separation-diagram.md
skills-separation-quickref.md
inclusive-defaults.md
karpathy-derivation/
project-brief.md
knowledge-corpus/
qa-testing-tiers.md
lessons-learned.md
metadata.md
metrics/
cache-hit-dashboard.md
skills-scoring-rubric.md
tome-research-quality.md
optimization-patterns.md
performance/
hooks.md
README.md
plugin-dependencies.json
plugin-dependencies.md
plugin-development-guide.md
quality-gates.md
skill-description-guide.md
skill-integration-guide.md
testing-guide.md
LICENSE
Makefile
plugins/
abstract/
.claude-plugin/
metadata.json
plugin.json
agents/
insight-engine.md
meta-architect.md
plugin-validator.md
skill-auditor.md
skill-evaluator.md
skill-improver.md
bin/
PROVENANCE.md
skrills_fallback.py
skrills-or-fallback
commands/
aggregate-logs.md
analyze-skill.md
bulletproof-skill.md
context-report.md
create-command.md
create-hook.md
create-skill.md
evaluate-skill.md
hooks-eval.md
improve-skills.md
make-dogfood.md
plugin-review.md
promote-discussions.md
rules-eval.md
skills-eval.md
test-skill.md
validate-hook.md
validate-plugin.md
config/
abstract_config.yaml
make/
common.mk
CONVENTIONS.md
docs.mk
markdown-only.mk
python.mk
data/
makefile_target_catalog.yaml
overlap_mappings.yaml
docs/
adr/
0001-2025-12-04-architecture-governance-process.md
README.md
template.md
architecture-evolution.md
claude-code-compatibility.md
compatibility/
compatibility.md
compatibility-features-march2026-early.md
compatibility-features-march2026-recent.md
compatibility-features-plugin-compat.md
compatibility-features.md
compatibility-patterns.md
examples/
hook-testing/
comprehensive-examples.md
modular-skills/
advanced-patterns/
modules/
cross-cutting-concerns.md
dynamic-loading.md
hierarchical-dependencies.md
README.md
basic-implementation/
README.md
complete-skills/
development-workflow/
modules/
code-review.md
deployment-procedures.md
documentation-guidelines.md
git-workflow.md
testing-strategies.md
SKILL.md
README.md
sample-migration/
sample-migration.md
modules/
focused-modules.md
hub-extraction.md
migration-results.md
original-analysis.md
shared-scripts.md
frontmatter-exceptions.md
governance.md
Makefile
makefile-dogfood.md
migration-guide.md
model-optimization-guide.md
multi-plugin-design.md
python-structure.md
skill-assurance-framework.md
skill-selection.md
wrapper-development-guide.md
examples/
test-skill-migration-example.md
hooks/
agent_dispatch_guard.py
aggregate_learnings_daily.py
homeostatic_monitor.py
hooks-observability.json
hooks.json
post_learnings_stop.py
post-evaluation.json
pre_skill_execution.py
pre-skill-load.json
shared/
__init__.py
dir_utils.py
hook_io.py
skill_utils.py
skill_execution_logger.py
Makefile
openpackage.yml
pyproject.toml
README.md
scripts/
__init__.py
abstract_validator.py
aggregate_skill_logs.py
auto_promote_learnings.py
cli_scaffold.py
compliance_checker.py
context_optimizer.py
deferred_capture.py
discussion_enrichment.py
dogfooder/
__init__.py
parser.py
reporter.py
validator.py
finding_verifier.py
hook_validator.py
improvement_suggester.py
insight_analyzer.py
insight_palace_bridge.py
insight_registry.py
insight_types.py
lenses/
__init__.py
delta_lens.py
health_lens.py
pattern_lens.py
trend_lens.py
makefile_dogfooder.py
module_validator
post_insights_to_discussions.py
post_learnings_to_discussions.py
... 1600 moreShowing a partial view of a very large repo.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic