By Acendas
Acendas Atlassian Suite — unified Jira Cloud, Confluence Cloud, Bitbucket Cloud, and QMetry Test Management integration for Claude Code. Jira + Confluence + Bitbucket + QMetry tools, workflow skills, and a multi-scanner PR review pipeline.
Router for the full Acendas Atlassian Suite. Use when: (1) the task spans multiple products (Jira + Confluence + Bitbucket + QMetry), (2) the user is unsure which specialist to use, (3) the request involves QMetry test management (no specialist exists — handled here via skills), or (4) the user asks to fetch/show/summarize a Jira issue (route to as-jira-issue, which auto-checks QMetry test cycles when QMetry is configured — never use raw jira_get_issue for issue summaries). Trigger phrases: 'Atlassian task', 'cross-product', 'weekly digest', 'test coverage for issue', 'QMetry', 'test case', 'test cycle', 'fetch issue', 'show issue', 'summarize ticket', 'what tests cover', 'search test cases', 'update execution result'. Routes to: 6 Atlassian specialists for Jira/Confluence/Bitbucket work; as-jira-issue for issue details (includes QMetry); as-qmetry-search / as-qmetry-testcase / as-qmetry-coverage for test management. Examples: <example> Context: Multi-product digest user: 'Weekly engineering digest — merged PRs, closed issues, new docs, deployment summary' assistant: 'Dispatching atlassian-orchestrator to coordinate across specialists.' <commentary>Hits code-review + sprint + release + devops + knowledge sources. Router fans out and aggregates.</commentary> </example> <example> Context: QMetry — test coverage from a Jira issue user: 'Show me the QMetry test coverage for PROJ-123' assistant: 'Running as-qmetry-coverage for PROJ-123.' <commentary>Jira project ID = QMetry project ID. No specialist needed — router drives the skill directly.</commentary> </example> <example> Context: QMetry — search test cases user: 'Search test cases in the PROJ project' assistant: 'Running as-qmetry-search for project PROJ.' <commentary>QMetry project key matches Jira project key. Router resolves the numeric ID via qmetry_list_projects.</commentary> </example> <example> Context: QMetry — update execution result user: 'Mark test case PROJ-TC-5 as PASS' assistant: 'Running as-qmetry-testcase PROJ-TC-5 with action update-execution.' <commentary>Router auto-resolves project_id from the test case key prefix.</commentary> </example> <example> Context: Clear specialist match user: 'Plan next sprint from backlog' assistant: 'Use sprint-orchestrator — that is a clear sprint planning task.' <commentary>Router declines and points to the right specialist.</commentary> </example>
Use this agent for autonomous, multi-step code review work on Bitbucket pull requests with Jira context. Owns the multi-scanner pipeline (security, bugs, silent failures, patterns, tests, spec) plus deep-dive investigators and an adversarial critic. Trigger on phrases like "review PR
You are the DevOps Orchestrator for the Acendas Atlassian Suite. You own Bitbucket Pipelines, deployments, environments, branch protection, code insights, and related CI/CD plumbing.
You are the Knowledge Orchestrator for the Acendas Atlassian Suite. You own Confluence read, write, and edit operations: pages, spaces, comments, labels, attachments, version history.
Adversarial PR critic with anti-sycophancy directive. Challenges PRs against their Jira spec using assumption extraction, pre-mortem narrative, and structured criteria. Surfaces blind spots the scanners miss. Read-only. Spawned by code-review-orchestrator on high-stakes PRs (large diff, payments/auth/data, or release-bound).
List or manage Bitbucket branch protection rules.
Search code across the Bitbucket workspace.
Show a Bitbucket commit's diff and CI status.
Manage attachments on a Confluence page.
Add a footer comment on a Confluence page.
Admin access level
Server config contains admin-level keywords
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.
Has parse errors
Some configuration could not be fully parsed
Has parse errors
Some configuration could not be fully parsed
Comprehensive Claude Code plugin for Jira Cloud + Confluence Cloud + Bitbucket Cloud, built on a single Node MCP server (@acendas/atlassian-mcp) with 29 workflow skills and an orchestrator agent.
| Component | Count |
|---|---|
| MCP server (Node, FastMCP) | 1 |
| MCP tools | 179 |
| Skills | 29 |
| Agents | 7 (1 router + 6 specialists) |
| Product | Tools | Coverage |
|---|---|---|
| Bitbucket Cloud | 122 | PRs, branches, branch restrictions, repos, file contents, forks, commits, comments, tags, pipelines, schedules, pipeline variables (repo/workspace/project), deployments, environments, env variables, code insights (reports + annotations + build statuses), native issues, snippets, webhooks, projects, code search, deploy keys, SSH keys, users, workspace metadata + members + permissions |
| Jira Cloud | 38 | Issues (CRUD + batch), transitions, comments, worklogs, watchers, links, remote links, changelogs, fields, custom fields, projects, components, versions, users, agile boards, sprints, JQL search |
| Confluence Cloud | 19 | Pages (CRUD), search (CQL), space tree, version history, version diff, comments + replies, labels, attachments, spaces, user search |
Cross-product (11): init, link-pr-to-issue, pr-summary-to-jira, sprint-status, standup-notes, sprint-retro, release-notes, publish-release-notes, review-pr, create-issue, triage-issue
Bitbucket (8): pr-list, pr-create, pipeline-status, pipeline-trigger, deployments, code-search, commit-show, branch-protection
Jira (5): jql-search, jira-issue, jira-sprint, jira-link, jira-worklog
Confluence (6): confluence-search, confluence-page, confluence-edit, confluence-tree, confluence-comment, confluence-attachment
All user-invokable as /atlassian-suite:<skill-name>.
Each agent has a focused tool surface + specialized system prompt for autonomous, multi-step work.
| Agent | Owns | Color |
|---|---|---|
atlassian-orchestrator | Router — dispatches to specialists or coordinates multi-specialist flows | blue |
code-review-orchestrator | Bitbucket PRs — review, comments, approve/decline, reviewers, with Jira context | cyan |
sprint-orchestrator | Jira Agile — boards, sprints, planning, retros, standup, active-sprint health | green |
release-orchestrator | Bitbucket merged PRs + Jira fixVersion + tags + Confluence publish | orange |
devops-orchestrator | Pipelines, deployments, environments, branch protection, code insights, schedules, variables | red |
triage-orchestrator | Jira issue lifecycle — bulk triage, create, link, watchers, batch transitions | yellow |
knowledge-orchestrator | Confluence read/write/edit — pages, spaces, comments, attachments, version diff | purple |
For most tasks, dispatch the specialist directly. Use atlassian-orchestrator only when intent is unclear or the work spans 3+ specialists end-to-end.
code-review-orchestrator runs a multi-scanner pipeline modeled on Shipyard's pattern. All scanners write strict YAML output with confidence ≥ 80 and a TRUNCATED protocol for large diffs.
Wave 1 — 6 parallel scanners (sonnet, ≤8 files per round, single-responsibility):
• pr-review-bugs — logic errors, null handling, races, leaks
• pr-review-security — injection, auth bypass, secrets, crypto
• pr-review-silent-failures — empty catches, swallowed errors, masked failures
• pr-review-patterns — project rules, naming, anti-patterns, duplication
• pr-review-tests — coverage, weak assertions, missing edge cases
• pr-review-spec — Jira AC compliance, under/over-building
↓
Wave 2 — pr-investigator (opus): deep-dives on borderline findings (conf 80–89, must-fix on auth/payments)
↓
Wave 3 — pr-critic (opus, high-stakes only): anti-sycophancy adversarial pass with assumptions + pre-mortem + structured criteria
↓
Consolidated verdict + optional inline-comment posting
Use via /atlassian-suite:as-review-pr <pr-id> [--high] [--quick] or by dispatching code-review-orchestrator directly for batch reviews.
node --version)npm install -g pnpm)Clone or copy this repo into your Claude Code plugins directory.
Build the MCP server:
cd server
pnpm install
pnpm build
Configure credentials. Two options — pick one:
npx claudepluginhub acendas/acendas-marketplace --plugin atlassian-suiteAI-agent-driven Android debugger — exposes JDI/JDWP and a JVMTI agent as MCP tools for Claude Code to drive. v1.8 adds standalone, attach-free static analysis backed by SootUp 2.0.0: static_class_hierarchy / static_call_graph / static_cfg / static_package_graph return agent-facing nodes/edges/truncated/warnings plus ASCII and Mermaid renderings, with BFS depth/node-cap bounds, virtual-dispatch-target capping, and Kotlin-synthetic collapse (companions, lambdas, DefaultImpls, coroutine continuations). New /android-debugger:ad-graph skill resolves class_dirs across Gradle modules and android_api_level, with a confirm-then-write Mermaid-persistence flow — routed as a 'Zeroth check' for pure structural questions ('what implements X', 'call graph of Y', 'class hierarchy of Z') ahead of the Debug-Plan shapes, and available mid-plan as a read-only side-query. v1.7 shipped Debug Plans: the agent authors a Plan declaring setup breakpoints, on_event handlers with actions (snapshot, FEEL expressions, eval_method, resume/step, yield_when, abort_when, log, set_var), hypotheses graded matched/contradicted/inconclusive, and a streaming plan_progress event feed. New MCP tools: run_debug_plan, pause_plan, abort_plan, validate_plan, list/save/load/delete_plan. New dbg.* FEEL namespace (instance_count, is_reachable, thread_state, frame_count, has_capability, elapsed_ms, logcat_since). Hybrid concurrency: read-only inspection passes through during a plan; mutating tools return vm_in_plan. Recipe skills /ad-catch /ad-trace /ad-walk /ad-bisect-flaky author plans; /ad-explain stays imperative; /ad-investigate dispatches templates and handles yield→abort→re-author. Plus everything from v1.0–v1.6: JVMTI deepening (native-speed heap walks count_instances / iterate_heap_by_class / find_referrers / find_referrer_chain auto-routing, line-rate method tracing with leaky-bucket throttling + arg + return-value capture, class-allowlisted allocation tracing, agent v3 JSON-RPC), HotSwap (hot_swap_class + hot_swap_classes + hot_swap_revert), the goal-driven /android-debugger:patch skill, breakpoints (line, conditional, hit-count, logpoint, exception, method, field, class-load), watches, step, FEEL expression evaluation (kfeel), eval_method with mutation refusal, frame snapshots, logcat, heap dump, session persistence, and the C++ JVMTI agent (3 ABIs). Cross-platform: macOS, Linux, Windows.
Turn your idea into working code — Shipyard runs Claude Code through a spec-driven agile sprint lifecycle: discuss features, plan sprints, build with TDD, review, and ship.
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.
Atlassian Jira and Confluence integration via Remote MCP Server for issue tracking, documentation, and project management
Complete JIRA automation suite with 14 specialized skills - issue management, agile workflows, time tracking, service management, bulk operations, and more
Comprehensive Jira integration with auto-detection of issue keys
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review