By baranovxyz
Keeps agent-facing repository memory layered, current, and maintainable across AGENTS.md, monorepos, docs, skills, agents, hooks, CLI, and MCP surfaces.
Designs autonomous worker agents when projects need subagents, role boundaries, trigger metadata, or separation between agents and workflow skills.
Audits agent-facing repository memory when AGENTS.md, CLAUDE.md, .claude/rules, docs, skills, agents, hooks, CLI, MCP, or plugin setup need qualitative evaluation.
Maintains agent-facing docs when approved changes need updates to AGENTS.md, CLAUDE.md, .claude/rules, docs, runbooks, or troubleshooting guidance.
Designs focused skills when repeated procedures need extraction, existing skills need improvement, or skill descriptions need compatibility-safe trigger metadata.
Designs focused skills and agents when repeated tasks, checklists, prompts, project procedures, user-invoked workflows, specialized review roles, subagents, or skill ideas need the smallest automation artifact.
Aligns host-specific instruction files and capability configs when working with CLAUDE.md, Cursor rules, Copilot instructions, GEMINI.md, hooks, MCP configs, LSP configs, plugin manifests, or marketplace entries.
Routes repository-memory work through the layered agent-ready model when working with AGENTS.md, CLAUDE.md, monorepos, docs, skills, agents, hooks, CLI/MCP decisions, tool-specific files, plugin manifests, or agent-ready migrations.
Closes out a coding session when the user says wrap up, ship it, finalize, or commit and PR — audits findings, promotes durable knowledge to spec / AGENTS / code, mutates the active continuation prompt in place (or writes a new one only when the spec direction changed), branches, commits, opens a PR, and merges.
Evaluates agent-facing repository memory when auditing AGENTS.md, CLAUDE.md, monorepo context, docs, skills, agents, hooks, CLI, MCP, plugin setup, or migration needs, and produces evidence-backed plans without editing.
Uses power tools
Uses Bash, Write, or Edit tools
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.
Tool-neutral repository context and memory tooling for coding agents. This repository is packaged as a Claude Code marketplace, while the guidance inside agent-ready-repo is designed to remain useful for Claude Code, Cursor, Codex, OpenCode, and other agent hosts.
agent-ready-repo - keeps agent-facing repository memory layered, current, and maintainable across AGENTS.md, docs, skills, agents, hooks, CLI, and MCP surfaces.spec-driven - authoring and evolution workflow for living specs and ADRs: keeps docs/specs the source of truth and docs/adr the immutable decision log.The repo ships parallel marketplace manifests for three hosts. The plugin body (skills/, agents/, hooks/, AGENTS.md) is shared; only the thin .{host}-plugin/ wrappers differ per host.
/plugin marketplace add <owner>/agent-context-kit
/plugin install agent-ready-repo@agent-context-kit
/plugin install spec-driven@agent-context-kit
Reload during an active session with /reload-plugins.
After Cursor's marketplace picks up the repo (or via team marketplace setup), install agent-ready-repo and/or spec-driven. Cursor reads .cursor-plugin/marketplace.json at the repo root and plugins/<plugin>/.cursor-plugin/plugin.json per plugin. See the Cursor plugins reference for current install flows.
Codex reads .agents/plugins/marketplace.json at the repo root and plugins/<plugin>/.codex-plugin/plugin.json. Add the marketplace via the Codex CLI's plugin marketplace flow (see Codex plugin docs) and select agent-ready-repo or spec-driven from the picker.
For Claude Code, from the parent directory of your local checkout:
/plugin marketplace add ./agent-context-kit
/plugin install agent-ready-repo@agent-context-kit
/plugin install spec-driven@agent-context-kit
Or from inside the checkout:
/plugin marketplace add .
/plugin install agent-ready-repo@agent-context-kit
/plugin install spec-driven@agent-context-kit
For direct plugin development without the marketplace layer (point --plugin-dir at the plugin you're working on):
claude --plugin-dir ./plugins/agent-ready-repo
claude --plugin-dir ./plugins/spec-driven
Each plugin is versioned independently (currently agent-ready-repo 0.5.0, spec-driven 0.2.0).
When publishing a release for a plugin, bump its version in the three marketplace entries plus its three per-plugin manifests so all hosts receive updates:
.claude-plugin/marketplace.json.cursor-plugin/marketplace.json.agents/plugins/marketplace.jsonplugins/<plugin>/.claude-plugin/plugin.jsonplugins/<plugin>/.cursor-plugin/plugin.jsonplugins/<plugin>/.codex-plugin/plugin.jsonbin/agent-ready-check warns when these drift.
For git-backed Claude Code marketplace version resolution, tag releases using Claude Code's plugin tag convention:
cd plugins/agent-ready-repo
claude plugin tag --push
Use --dry-run first when preparing a release.
Before making the repository public:
python3 plugins/agent-ready-repo/bin/agent-ready-check --root . --json.npx claudepluginhub baranovxyz/agent-context-kit --plugin agent-ready-repoAuthoring and evolution workflow for living specs and ADRs: keeps docs/specs the source of truth and docs/adr the immutable decision log.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
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.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications