guardrails-coding-agent
claudeShared guardrails layer for all coding agent families — enforces safety, quality, governance, observability gates, and optional ChromaDB vector memory for semantic session recall
15 skills · 3 commands · hooks
Single-ticket implementation coordinator — fetches a Jira or Azure DevOps Boards ticket, routes to domain agents via multi-signal scoring, produces story-plan.md for approval, then sequentially invokes each domain agent with cross-domain context handoff, semantic memory retrieval, and a final cross-domain review
Plugin story-coding-agent from marketplace software-agents-team in gagandeepp/software-agent-teams. Commands read from the repo's manifest — 1 month ago.
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.
story-board-connectorDispatches to the official Jira MCP server or Azure DevOps MCP server based on boardSource from resolved config. Validates ticket ID format before calling MCP. Maps ADO work item fields to the unified Jira-compatible raw object shape so ticket-normalizer and label-classifier require no changes. Rece
commit-push-prUse when committing, pushing, and raising a PR — stages changed files, writes a Conventional Commits message, pushes to the remote branch, creates a GitHub PR via gh CLI, then posts the PR URL to configured Slack or Teams channels for review. Channel targets are configurable via .commit-push-pr.json
story-config-resolverResolves the Story agent configuration by reading .story-agent.json and applying a 5-level resolution order: per-invocation override > directory mapping > auto-detection > config defaults > plugin defaults. Enforces the guardrails prerequisite (fail-closed) and checks sprint-jira module availability
story-context-bridgeRuns after each domain agent completes. Extracts a structured summary from the agent's output by scanning files modified during its run. The summary is injected into the next domain agent's context packet so downstream agents have concrete artifact references (table names, API endpoint URLs, compone
story-contract-validatorProactive inline guardrail that runs at two seams in the domain-agent execution loop: after db-coding-agent completes (before backend starts) and after backend-coding-agent completes (before frontend starts). Reads the actual artifact files produced by the completed agent, builds a verified inventor
story-cross-domain-reviewRuns a final code review across all files touched by all domain agents for this story. Checks cross-domain consistency: API contract alignment (URL path + HTTP method + request/response payload shape), DB schema consistency (table names + column names), env var consistency, and TypeScript type consi
story-domain-invokerThe execution engine for story-coding-agent. Checks for user approval of story-plan.md, then sequentially invokes each domain agent from the executionSequence as a sub-agent, building a context packet (full ticket + agent-specific scope + completed agent summaries) for each invocation. Halts immedia
story-domain-routerApplies the four-signal weighted scoring model to a single InternalTicket to determine which domain agents should implement the story. Unlike the sprint router (single-agent assignment), the story router is multi-assignment: all agents with confidence >= threshold are assigned. Uses label(0.4) + com
story-execution-sequencerTakes the list of assigned domain agents from domain-router and produces a deterministic, dependency-ordered execution sequence by filtering the canonical dependency order (DB → backend → frontend → devops → security) to only the assigned agents. Confidence score does not affect ordering; domain top
story-guidelines-ingestionReads and merges story agent guidelines across three layers: plugin defaults (bundled), team custom (.story-guidelines.md), and per-invocation override. Uses section-level (## heading) replacement: a higher layer section fully replaces the same-named section from a lower layer.
story-plan-generatorConsumes routing assignments and execution sequence to produce story-plan.md in the configured outputDir. The plan is the human approval gate — no domain agent is invoked until the user explicitly approves. Surfaces routing analysis (all five agent scores), implementation sequence, per-agent scope,
story-repo-orchestratorRuns after story-plan.md approval, before domain-invoker. For each agent in executionSequence, reads the repository block from the agent's config file (.backend-agent.json etc.), clones the repo if the localPath does not exist on disk, then runs `claude config init --non-interactive` in the localPat
story-guardrailsGuardrails adapter for story-coding-agent. Delegates input validation (Jira ticket content), output validation (story-plan.md), harm prevention, budget monitoring, idempotency guard, cost tracking, and audit trail to guardrails-coding-agent. Called twice per run: pre-work (input gate) and post-work
story-memory-writerUse at the end of /story-implement to append a completion record to .story-memory.jsonl, enabling cross-session tracking of which tickets have been implemented. Emits a non-blocking MEMORY WARN when the ticket has been completed in a prior session.
story-task-creatorRuns after repo-orchestrator, before domain-invoker. Creates one linked child task per agent in executionSequence in the configured board (Jira or Azure DevOps). Task title: "[{ticketId}] {agentName} implementation". Description: scope bullets from the agent's section in story-plan.md. Linked as chi
story-ticket-fetchFetches and normalises a single ticket by ID using board-connector (Jira MCP or Azure DevOps MCP) plus the sprint-jira module's ticket-normalizer and label-classifier skills. Produces one fully annotated InternalTicket with domainSignals populated, ready for domain-router. Hard-blocks if storyBoardA
/story-coding-agent:story-implementFetches a single ticket by ID from Jira or Azure DevOps Boards, routes to domain agents via multi-signal scoring, produces story-plan.md for user approval, then sequentially invokes each domain agent (DB → backend → frontend) with cross-domain context handoff and a final cross-domain review.
/story-coding-agent:story-initScaffolds .story-agent.json in the workspace root. Checks codebase availability (prompts for local path or GitHub URL, with optional repeated prompts to add more repos), prompts for board source (Jira or Azure DevOps Boards), reads board config from env vars, validates board MCP server and sprint-ji
story-agentMulti-domain implementation coordinator for a single project management ticket (Jira or Azure DevOps Boards). Fetches the ticket, routes to domain agents via multi-signal scoring, produces story-plan.md for user approval, then sequentially invokes each domain agent (DB → backend → frontend) with cro
"${CLAUDE_PLUGIN_ROOT}/hooks/run-session-start"
"${CLAUDE_PLUGIN_ROOT}/hooks/run-posttooluse-sync"
"${CLAUDE_PLUGIN_ROOT}/hooks/run-stop-memory"
Shared guardrails layer for all coding agent families — enforces safety, quality, governance, observability gates, and optional ChromaDB vector memory for semantic session recall
15 skills · 3 commands · hooks
Core frontend coding agent — config resolution, component-first routing, accessibility review, guidelines ingestion for React/Angular/Vue, and optional vector memory
13 skills · 2 commands · 1 agent · hooks
Core Playwright test automation agent — config resolution, test-type detection, framework-aware selectors, test execution, boilerplate scaffolding, guardrails integration for E2E, API, and visual regression testing
11 skills · 2 commands · 1 agent · hooks
Polyglot database coding agent for SQL Server, PostgreSQL, MongoDB, and Azure Cosmos DB with LSP, custom guidelines, org governance, and optional vector memory
10 skills · 2 commands · 1 agent · hooks
Polyglot backend coding agent for C#, Go, Java, and Node.js with LSP, custom guidelines, org governance, and optional vector memory
9 skills · 2 commands · 1 agent · hooks
Core DevOps coding agent — config resolution, platform detection, Dockerfile generation, guidelines ingestion, template repo integration, pipeline review, and optional vector memory
8 skills · 2 commands · 1 agent · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
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
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
6 skills · 7 commands · 4 agents
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.