Plugin Claude Code
A governed, portable engineering platform for coding agents: the governance layer (agentic-os), the SDLC pipeline that runs on it (agentic-sdlc), and a standalone Quality Engineering blueprint catalog and scaffolder (agentic-qe). Evidence-grounded repo discovery, audited agent contracts, HITL escalation, and hard…
Plugin Claude Code
The governance layer for coding agents. /agentic-init interviews you (role presets, HITL dial, stack) and scaffolds a governed multi-agent architecture into your repo: canonical agent contracts, enforcement hooks, escalation policies, instruction-quality gates, and generated stack-specific agents.
Skill Claude CodeCodex
Standalone verifier for an agentic-os install — checks the file manifest against the install journal, py-compiles AND imports every hook it owns (a badly-rendered scalar compiles but raises on load), dry-runs the enforcement hooks with canned events (block hooks must exit 2 on a synthetic violation, 0 on clean), runs…
Skill Claude CodeCodex
Install the agentic-os process layer into the current repo — interview (role presets, HITL dial, autonomy matrix, stack confirm, adapters), dependency registration, template scaffold, stack-specific agent generation with instruction-quality audit, then doctor verification. Journaled and resumable. Use when the user…
Skill Claude CodeCodex
Remove one or more role presets from a repo's scaffolded agentic-os layer, or the whole layer with --all — not by deleting a role's files, but by recomputing the desired state for the remaining preset union and converging the repo to it, so the result equals a fresh install of the roles that stay. Set-difference over…
Skill Claude CodeCodex
Upgrade a repo's scaffolded agentic-os layer to the currently installed plugin version — per-file three-way reconciliation via the install journal's recorded sha256 (unchanged managed files overwritten, user-modified files diffed and prompted, managed blocks replaced wholesale, generated agents offered regeneration…
Plugin Claude Code
Tool-agnostic AI blueprints for Quality Engineering, organized by STLC stage and written in the agentic-os design language: blast-radius role tags, human review gates, and model tiers. The qe-blueprints skill scaffolds a ready-to-fill agent framework from a chosen blueprint; the eval-harness skill generates a…
Skill Claude CodeCodex
Scaffold a two-layer eval framework — deterministic contract checks plus optional LLM-judge behavioral cases — for every Claude Code skill (and agent file) in a repository. Invoke when the user asks to add evals, regression guards, or skill tests, to wire eval automation into hooks/CI, or to extend an existing…
Skill Claude CodeCodex
Invoke when the user wants to start, scaffold, bootstrap, or implement a quality-engineering blueprint or an agentic test-automation setup — interviews the user, matches intent to one of 28 bundled QE blueprints, and generates a fill-in-ready agent framework (context file, agent stubs, skill stubs) for Claude Code…
Plugin Claude Code
Runs coding agents through a governed delivery lifecycle: plants a repo-guides documentation baseline, drafts stories from raw asks, and carries the work through requirements, spec, plan, build, and QA stages behind gate-arbiter judgment gates (spec.approved, plan.approved, qa.drift, code-review.final…
Agent
Dispatch codebase-scout before any complexity scoring or brainstorming phase runs, whenever the pipeline needs grounded, read-only facts about the existing codebase rather than assumptions. It never plans or writes implementation code — its only output is a single technical-analysis.md research artifact that…
Agent
Use this agent when a feature branch has introduced structural or architectural changes and the guide corpus under .agentic/guides/ needs to be checked for drift. It is the standard dispatch target for mr-watch immediately after a merge lands, and repo-guides also points to it whenever ongoing sync against the guide…
Agent
Dispatch this agent whenever the gate-arbiter needs an autonomous stand-in tech-lead judgment at one of the three gates it owns: spec.approved, plan.approved, or qa.drift. It runs after the router's own deterministic pre-checks (evidence-file shape, per-task test-first declaration format) have already passed, and it…
Agent
Dispatch this agent whenever a task's size is not obvious from cheap heuristics and the orchestrator needs a defensible, six-dimension complexity score plus a routing call (plan directly vs. brainstorm first vs. split before planning). It never designs or writes code — it reads what earlier phases already learned…
Agent
Use this agent when gate-arbiter dispatches a requirements.ambiguous or spec.clarification judgment gate during an autonomous SDLC run and no human is available to answer synchronously. story-proxy resolves the open question by applying a fixed, priority-ordered rule set against the original task, supplied artifacts…
Skill Claude CodeCodex
Required functional proof for anything user-visible, run right after gate-runner. When a change touches UI or another externally visible surface, it reuses e2e coverage that already exists, or generates a focused Playwright check when none does; either way it captures screenshots, console output, and network errors…
Skill Claude CodeCodex
Resolves the SDLC code-review gate with a multi-lens review fan-out and persists one canonical verdict JSON as the hand-off back to gate-arbiter. Invoked inline (Skill tool) by gate-arbiter at gate ids code-review.final (full multi-lens pass after implementation evidence) and code-review.check (narrow re-check of…
Skill Claude CodeCodex
Standalone, on-demand multi-lens code review of local git changes, outside any managed SDLC pipeline. Invoke when the user says "code review", "review my changes", "review my code", "review my branch", "review staged changes", "review this diff", or "run a code review" — and no pipeline is already driving the review.…
Skill Claude CodeCodex
Thin gating skill that classifies a task's complexity when the caller's own heuristics cannot confidently route it. Invoke when you need to decide between going straight to detailed planning versus running a design/ideation pass first, or when a task might be too large to plan directly. Trigger phrases include "score…
Skill Claude CodeCodex
Invoke this skill whenever an SDLC pipeline phase reaches a judgment gate and needs a resolved, logged verdict — spec approval, plan approval, QA drift, code review (final or check round), requirements ambiguity, spec clarification, or feature verification. Trigger phrases include "resolve this gate", "route this…
Skill Claude CodeCodex
Run the host project's quality gates in a fixed order (lint -> build -> unit tests -> affected tests -> optional UI tests) and return a structured, machine-readable merge-readiness report. Runner-agnostic: detects the build tool (npm/pnpm/yarn/cargo/poetry/uv/go) from manifest files, caches a gate plan, and defers…
Skill Claude CodeCodex
Commit with a mandatory ticket reference, push, and open an MR or PR. Commit, branch, and title conventions are read from .agentic/guides/standards/git-workflow.md; the MR/PR adapter (a CLI, MCP server, or custom command) is read from the ## Review Adapter section of .agentic/guides/project.md. No source-control…
Skill Claude CodeCodex
Watch one open MR/PR and autonomously clear whatever blocks merge — CI failures, requested-change reviewer comments, and merge conflicts — on a polling loop until the request merges, closes, or the user stops it. Adapter-driven: no source-control platform is hardcoded. Invoke when the user says "watch the MR"…
Skill Claude CodeCodex
Bootstrap the QA knowledge foundation for a repo: discover test files, coverage reports, CI test gates, and QA docs; configure adapters to external QA sources (test-case management, QA documentation, external test repos); then write two persistent guides — qa-strategy.md and qa-health.md — under…