kendex.ai

Marketplaces / vanillagreencom/kendex

kendex

Featured

The official kendex catalog: agents, skills, hooks and Pi extensions for AI coding harnesses

github.com/vanillagreencom/kendex· by vanillagreen· MIT· @ a7ca9af

Subscribe

$kendex marketplace subscribe vanillagreencom/kendex

Its packages then sit beside everything else you have. Every install is checked on your machine first.

Bundles

4

Groups of packages that work well together.

Packages

42
PackageKind
generalist

General-purpose agent for documentation, cleanup, stale references, code organization, and miscellaneous maintenance tasks.

agent
iced

Iced UI specialist. Use for Iced widgets, Canvas/Shader rendering, pane_grid layout, Theme system, Subscription-based data flow, or Elm Architecture patterns.

agent
planner

Planning specialist that explores requirements and code context, weighs architecture trade-offs, and produces ordered implementation plans or plan files. May write planning artifacts; does not edit production code.

agent
researcher

Exa-powered research specialist for producing evidence-backed findings reports from project research prompts. Use for research issues, technology investigations, vendor/library comparisons, architectural option analysis, and current-state web research.

agent
reviewer-arch

Architecture reviewer for design reviews, module boundary validation, spec/proposal review, and technical debt assessment.

agent
reviewer-correctness

Broad correctness and regression reviewer for behavior breakage, boundary/edge-case predicates, API/CLI/devex regressions, feature-gate leaks, migrations, state semantics, and cross-module side effects.

agent
reviewer-doc

Documentation accuracy reviewer. Verifies changed doc claims against implementation, re-derives transcribed values, checks citations resolve, audits drift.

agent
reviewer-error

Silent failure and error handling reviewer. Detects fail-open paths, swallowed errors, wrong-cause diagnostics, and inadequate error propagation.

agent
reviewer-perf

Performance validation specialist. Latency validation, benchmark execution, percentile analysis, hot-path cost review, regression detection.

agent
reviewer-quality

Code quality reviewer for maintainability, simplification, abstraction value, type boundaries, helper reuse, decomposition, and god objects.

agent
reviewer-safety

Memory, thread, and process safety auditor. Unsafe code, data races, lock-free correctness, and file/process races (TOCTOU, PID reuse, shared mutable state).

agent
reviewer-security

Application security reviewer. Auth logic, input handling, trust/ownership gating, path containment, and secret exposure.

agent
reviewer-test

Test coverage and quality reviewer. Verifies coverage, detects vacuous tests and missing must-fail controls, audits assertion tightness and test wiring.

agent
rust

Rust engineer for performance-critical systems. Use for zero-allocation hot paths, lock-free algorithms, SIMD optimization, and systems programming.

agent
scout

Fast reconnaissance agent for exploring codebases, finding files by pattern, searching keywords, answering architecture questions, and returning compressed cited context or report artifacts. Specify thoroughness: quick, medium, or very thorough.

agent
tpm

Technical Program Manager for analyzing roadmaps, project lifecycle, and progress. Returns recommendations only — does not modify project management tools.

agent
code-quality

Generic code-authoring standards for dev agents: correctness over convenience, no fail-open branches, comment rules, over-engineering limits, prove-your-guards. Load before writing or modifying code.

skill
decider

Architecture Decision Record (ADR) and architectural decision document management: templates, creation, search, supersession tracking, and INDEX maintenance.

skill
deep-research

Exa-powered deep research producing an evidence-backed findings.md report. Load for research tasks, architectural investigations, and vendor, library, or technology comparisons.

skill
dep-radar

Sweeps every pinned version in the repo — deps, SDKs, vendored forks, model weights — checks upstream, and lands upgrades with their fallout in one PR per surface. Load to run or tune a dependency sweep.

skill
dev

Dev-agent workflows for issue implementation and review-fix delegation, invoked by orch or specialist agents.

skill
github

GitHub API CLI for PR operations: threads, comments, reviews, CI logs, merging, and cross-PR analysis.

skill
growth-guards

Five repo growth guards beside size-ratchet — todo-ban, byte-ceiling, suppression-ban, conflict-markers, commit-msg — and the git hook shims that run them. Load to add, tune, or debug a check, the hooks, or GROWTH_GUARDS_* settings.

skill
iced-rs

Iced 0.14 GUI expert: custom widgets via iced::advanced, overlays, Canvas, Shader, pane_grid, theming, subscriptions, Elm architecture, with a bundled full-API reference. Load whenever building or debugging an Iced UI.

skill
linear

Bash CLI over Linear's GraphQL API with a local cache. Load for ANY Linear interaction: reading, searching, creating, or updating an issue, project, cycle, milestone, initiative, or label.

skill
orch

PRIMARY AGENT ONLY — work-item orchestration for Linear or GitHub issues: prepare, delegate implementation, review, submit, merge, hand off, and oversee fleets of sessions.

skill
preflight

Diff-scoped deterministic pre-review checks: shell parse/shellcheck errors, fail-open bash, unwired test suites, untrapped scratch dirs, directory creation at hardcoded temp paths, dead path citations, TODO markers, bot attributions, malformed JSON/TOML/workflows. Load to run, tune, or debug preflight.

skill
price-handling

f64 price patterns for trading systems. Load when: comparing prices, rounding to tick size, formatting for display/broker APIs, parsing market feeds, designing price types or SymbolSpec structs.

skill
project-management

TPM-orchestrated planning, audit, roadmap, and research-driven decomposition. Owns the user-facing wrappers (cycle-plan, audit-issues, roadmap-*, research-*) and the underlying TPM execution workflows.

skill
review-gate

Org-wide PR review gate: one predicate answers 'is this exact head reviewed?', one writer posts the answer as a merge-blocking commit status. Load to wire, adopt, tune, or debug a repo's gate or its REVIEW_GATE_* settings.

skill
reviewer

Strict review and QA workflows: reviewer ethos, code-review classification, the finding JSON schema, and the QA-label lifecycle. Load when reviewing a diff, classifying findings, or returning a verdict.

skill
second-opinion

Cross-model second opinion: review, challenge, audit, and consult via an external AI CLI (Claude ↔ Codex).

skill
size-ratchet

Tighten-only file-size gate: tracked files over their threshold (default 400, per-class via SIZE_RATCHET_CLASSES) are frozen in a baseline TSV that only moves down. Load to add, tune, or debug the ratchet, its baseline, or SIZE_RATCHET_* settings.

skill
trading-design

Professional trading UI design system. Load when designing or implementing panels, layouts, typography, color, data display, or interactions for trading applications.

skill
worktree

Git worktree management: create, list, remove isolated working copies with env/config symlinks.

skill
block-bare-cdhook
block-repo-copyhook
block-unsafe-rmhook
post-edit-linthook
pre-commit-checkhook
session-drift-checkhook
task-completed-checkhook