By ninja-agents
AI agent that audits repos for documentation completeness and scaffolds missing files
Add missing Activity Type field to completed Jira tickets. Fetches tickets matching a configured JQL filter, classifies each ticket's Activity Type based on issue type, labels, and summary keywords, previews proposed changes, and applies them after user approval. Trigger phrases: "add missing activity type", "fill activity type", "set activity type", "classify activity type", "activity type updater". <example> user: "/jira-add-missing-activity-type" assistant: "I'll fetch Done tickets missing Activity Type, classify them, and preview the proposed assignments." </example> <example> user: "/jira-add-missing-activity-type" assistant: "Reading config... Found 23 tickets missing Activity Type. Classifying based on rules..." </example>
Find resolved bugs missing a QA Contact and identify the verifier from comments and status transitions. Previews proposed assignments and applies them after user approval. Trigger phrases: "bugs missing QE", "missing QA contact", "find QE for bugs", "set QA contact", "bugs without QE". <example> user: "/jira-bugs-missing-qe" assistant: "I'll fetch resolved bugs missing QA Contact, analyze comments and changelogs to identify verifiers, and preview proposed assignments." </example> <example> user: "/jira-bugs-missing-qe" assistant: "Reading config... Found 14 bugs missing QA Contact. Analyzing comments and transitions..." </example>
Generate a QE (Quality Engineering) story from a dev Jira story. Reads the dev story, optionally reads repo context for richer acceptance criteria, generates QE description with test scenarios, previews for approval, then creates the story in Jira and links it. Trigger phrases: "qe story", "create qe story", "generate qe story", "qe acceptance criteria", "quality story from dev story". <example> user: "/jira-qe-story CNV-12345" assistant: "I'll read the dev story CNV-12345 and generate a QE story for it." </example> <example> user: "/jira-qe-story MTV-5678 --repo kubev2v/forklift-console-plugin" assistant: "I'll read MTV-5678 and use the forklift-console-plugin repo for context." </example>
Transition Jira sprint tickets based on linked GitHub PR/issue status. Fetches all tickets in a sprint, checks their linked GitHub PRs and issues, previews proposed status transitions, and applies them after user confirmation. Trigger phrases: "update sprint tickets", "transition tickets", "sync ticket status", "update jira from PRs", "sprint ticket updater". <example> user: "/jira-sprint-tickets-updater" assistant: "I'll fetch the active sprint tickets, check linked PRs/issues, and propose status transitions." </example> <example> user: "/jira-sprint-tickets-updater" assistant: "Reading config... Found 32 tickets in Sprint 5. Checking linked PRs and issues..." </example>
Estimate story points for unpointed Jira tickets by comparing against historical team data. Fetches Done tickets with SP from Jira, caches them locally, then uses Claude's reasoning to suggest SP values for new tickets. Adds a Jira comment with justification and sets the SP field. Trigger phrases: "estimate story points", "story point estimation", "SP estimation", "estimate SP", "point tickets", "size tickets". <example> user: "/jira-story-points CNV-12345" assistant: "I'll estimate story points for CNV-12345 by comparing it against historical team data." </example> <example> user: "/jira-story-points" assistant: "I'll find unpointed tickets in the backlog and estimate story points for each." </example>
External network access
Connects to servers outside your machine
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.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
github_patRequired for PR research and remote repo audits. Create at github.com/settings/tokens
${user_config.github_pat}
A shared playground for AI agents that help engineering teams ship status reports, run sprint retrospectives, and audit repository documentation. Each agent is a self-contained directory under agents/ with its own scripts, config, and data. Agents run inside Claude Code or Cursor via MCP servers that connect to GitHub, GitLab, and Jira.
Note: These agents are opinionated — they encode our team's specific workflows, naming conventions, and tooling choices. They work well for us but may need adaptation for your team.
The repo follows a "data collector + deterministic script" pattern: the AI agent fetches data from external services (GitHub, GitLab, Jira) via MCP tool calls and saves it as CSV, then a TypeScript script generates the structured output. The agent writes only the prose sections (e.g., Key Highlights, Key Takeaways) that require synthesis. Each agent is self-contained — no cross-agent imports, shared team config accessed via config path — and all dependencies are managed in the root package.json. TypeScript files execute directly via tsx with no build step.
git clone <repo-url> && cd ninja-agents
npm install # all dependencies (linting, TypeScript, testing)
# Set tokens as env vars (add to ~/.bashrc or ~/.zshrc to persist)
export GITHUB_PAT=ghp_xxxxxxxxxxxxxxxxxxxx
export GITLAB_PAT=glpat-xxxxxxxxxxxxxxxxxxxx
# Launch your IDE and invoke an agent
claude # Claude Code
# then type: /team-update
# Or open the project in Cursor
# then ask: @weekly-team-update or "generate a weekly team report"
See docs/mcp-setup.md for the full token setup guide and troubleshooting.
| Agent | Claude Code | Cursor | Description |
|---|---|---|---|
| weekly-team-update | /team-update | @weekly-team-update | Weekly team report for leadership from GitHub, GitLab, and Jira |
| sprint-review | /sprint-review | @sprint-review | Sprint retrospective analysis from active Jira sprint |
| sprint-planning-analysis | /sprint-planning-analysis | @sprint-planning-analysis | Sprint planning health-check against velocity baseline |
| repo-contextification | /repo-contextification | @repo-contextification | Audit repo docs and AI-readiness, scaffold missing files |
| jira-qe-story | /jira-qe-story | @jira-qe-story | Generate QE story from dev Jira story, create in Jira with link |
| jira-sprint-tickets-updater | /jira-sprint-tickets-updater | @jira-sprint-tickets-updater | Transition sprint tickets based on linked GitHub PR status |
| slack-channels-analyzer | /slack-channels-analyzer | @slack-channels-analyzer | Analyze Slack channels for UI-related topics and trends |
| jira-add-missing-activity-type | /jira-add-missing-activity-type | @jira-add-missing-activity-type | Add missing Activity Type to completed Jira tickets |
| jira-story-points | /jira-story-points | @jira-story-points | Estimate story points using historical team data |
| jira-bugs-missing-qe | /jira-bugs-missing-qe | @jira-bugs-missing-qe | Find resolved bugs missing QA Contact, identify and set verifier |
| (scaffold a new agent) | /create-agent | copy agents/_template/ | Scaffold a new agent with best-practice structure and specs |
Each agent has its own README with setup and usage instructions.
You need an AI-powered IDE plus MCP servers for the agents you want to use:
npx claudepluginhub ninja-agents/ninja-agents --plugin ninja-agentsMake your AI agent code with your project's architecture, rules, and decisions.
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.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Access official Microsoft documentation, API references, and code samples for Azure, .NET, Windows, and more.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.