claude

backlogd

Turn Claude Code into a problem-driven scrum team. You file problems as Linear issues; an agent team runs the empirical Scrum loop (scope, solve, review, adapt) and owns the solutions. An independent reviewer gates every increment against its acceptance criteria, the Definition of Done, and a standards corpus. Runs on your Claude subscription via the official Linear MCP over OAuth — no API keys.

3,741 on GitHubby Nicolai Bernsenv1.0.0MITupdated 2 days agoorchestration
/

Plugin backlogd from marketplace buildwithclaude in davepoon/buildwithclaude. Commands read from the repo's manifest — yesterday.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (8)

  • ac

    backlogd's contract for typed Acceptance Criteria — every `## Acceptance Criteria` item declares *how it is verifiable* via an optional `[test]` / `[manual]` / `[review]` prefix tag; untagged items default to `[review]` (backwards compatible). Load when shaping AC (`/backlogd:scope`) or judging a ve

  • develop

    The method a backlogd developer follows to turn one shaped issue into a solution — consult /docs (the living spec), treat the issue's ## Acceptance Criteria as the binding static target, ship a thin vertical slice with tests where they earn their keep, and verify against the AC before reporting solv

  • graph-navigation

    Query backlogd's local agent-execution + memory graph (.backlogd/graph/) — read-only. Records what only the loop knows (dispatch outcomes, latency, rework events) plus a low-signal aside of which files past problems touched. Use when a backlogd agent wants prior context before acting (problem-histor

  • linear

    backlogd's operating model for Linear via the official MCP. Use whenever a backlogd agent touches Linear — picking up a problem, deciding Issue-vs-Project structure, decomposing work into sub-issues, setting blocks/blocked-by, transitioning workflow state, reporting progress, or surfacing blockers.

  • retro

    backlogd's Sprint Retrospective mechanism — over a completed milestone (or a cycle / date / count fallback) the retro reads the execution graph as objective evidence, detects cross-issue patterns no single review can see, classifies each learning, and files the load-bearing ones as candidate `kind:i

  • reviewer

    The trust model behind backlogd's `backlogd:reviewer` subagent — fresh context, restricted tool grant, mandatory machine-verifiable check execution with cited evidence, judge/act split. Use when implementing or modifying `/backlogd:review`, the reviewer agent, or any caller that dispatches the revie

  • scrum

    backlogd's operating model for Scrum — the framework backlogd interprets and runs on. Use whenever a backlogd agent needs to reason about Scrum primitives: the three accountabilities (Product Owner, Scrum Master, Developers), the five events (Sprint, Sprint Planning, Daily Scrum, Sprint Review, Spri

  • worktree-isolation

    backlogd's per-session worktree isolation pattern — one isolated git worktree per concurrent agent session, the identity guard armed before any commit, the lock/no-prune convention, and the dedicated-clone escalation when the native pattern proves insufficient. Loaded when a worktree or parallel ses

Slash commands (7)

  • /backlogd:init

    One-time Linear workspace bootstrap — bring the team into backlogd's canonical shape (labels · workflow states · templates) by driving the local config engine. Opt-in, setup-only, key-free in the orchestrator; the engine reads the Admin key itself. Pass --dryrun to print the plan and touch nothing.

  • /backlogd:release

    Cut a release — promote the integration branch to the release branch, bump the plugin version on a release branch, merge with a merge commit, tag vX.Y.Z, and back-merge so the two branches re-sync.

  • /backlogd:retro

    Sprint Retrospective — over a completed milestone (or a cycle / date / count fallback), read the execution graph + what happened, detect cross-issue patterns, classify the load-bearing learnings, and file them as candidate `kind:improvement` issues for the PO to prioritize. The retro proposes; the P

  • /backlogd:review

    Quality gate — dispatch an independent reviewer subagent against a solved problem's acceptance criteria, then act on its verdict — accept to Done, send back to In Progress, or escalate a judgement call. The reviewer judges; the orchestrator acts.

  • /backlogd:scope

    Shape a Linear problem into an executable, decomposed issue — write acceptance criteria, decompose into sub-issues, sequence with blocked-by — then stop. No solving.

  • /backlogd:solve

    Execute a shaped Linear problem — dispatch a developer per unit of work in dependency order, record each result, and on the happy path auto-chain the independent verdict review and merge a fully-green increment to Done with no human gate (ship-on-green, on by default). Routes ops-only problems (kind

  • /backlogd:status

    Scrum-master standup — survey the active problems in Linear, report progress + blockers to the product owner, and refresh a rolling-7-day forecast onto the engagement Project's description.

Subagents (4)

  • developer

    Owns the solution to one backlogd problem. Dispatched by /backlogd:solve with a single problem to solve; takes a concrete action, writes its progress to its own Linear issue, and reports the outcome.

  • refiner

    drafts AC + decomposition for one backlogd problem; dispatched by /backlogd:scope and /backlogd:solve triage

  • reviewer

    Owns the verdict on a backlogd unit or solved problem. Dispatched in one of two modes — `pre-commit-gate` (gates a unit's diff before commit, inside /backlogd:solve) or `verdict` (drafts the user-facing AC + DoD verdict for an In-Review problem, inside /backlogd:review). Reads its issue + diff with

  • tester

    writes/expands tests proving the AC of one backlogd unit; dispatched by /backlogd:solve after developer

MCP servers (1)

  • linear

    connects to: https://mcp.linear.app/mcp

Hooks (2)

  • SessionStart

    sh "${CLAUDE_PLUGIN_ROOT}/hooks/check-git-identity.sh"

  • SessionStart

    sh "${CLAUDE_PLUGIN_ROOT}/hooks/session-bootstrap.sh"

View source on GitHub buildwithclaude.com

More from davepoon/buildwithclaude

All 277 plugins →

Complete collection of ~110 Claude Code skills across document processing, development, automation, CRM, DevOps, and more

200 skills

3,741

Complete collection of 174 slash commands across 22 categories

177 commands

3,741

Complete collection of 117 specialized AI agents across 11 categories

117 agents

3,741

gsd

claude

Get Shit Done -- a structured workflow plugin for Claude Code that adds planning, execution, and verification commands with MCP-backed project state

83 skills · 33 agents · 1 MCP server

3,741

forge

claude

Full-lifecycle SDLC orchestrator: a 12-stage pipeline (SRS, architecture, spec, plan, build, eval, deploy, monitor, release) driven by specialized agents, persistent cross-session memory, auto-reflection, gate enforcement, and semantic skill mining that proposes new skills from recurring workflows.

45 skills · 27 agents · hooks

3,741

suede-skills

claudecodex

74 skills for Claude Code and Codex. A build DAG researches your repo, fans out disjoint lanes, and refutes its own review before anything lands. A blunt A-F ship grade blocks the bad merge instead of complimenting it. The same folder designs the page, writes the copy, and ships native iOS and Android builds.

70 skills · 1 MCP server

3,741

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain backlogd?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins277 plugins