Opinionated orchestration of work through two delegation surfaces: dispatched workers (Codex CLI (GPT-6) and Claude subagents) via a task-strategy workflow with model and reasoning-effort routing, fenced write scopes, and independent two-worker verification; and sibling Claude Code sessions via a distribution workflow with session enumeration, mandatory dispatch-message blocks, and explicit stand-down closure. Ships 11 duty agent definitions that pin no model or effort; the routing table sets model and reasoning effort per checkpoint type at spawn time. Both skills are extendable at five workflow positions and via recognized named configuration values; the plugin ships hooks that deliver a project's per-skill extension files (.claude/extensions/work-orchestrator/) wrapped in a structural envelope.
2 skills · 11 agents · hooks
Author LLM-targeted content (prompts, skills, agents, rules files, session handoffs, and session feedback) for Claude 5 (including Opus 5.5, Sonnet 5.5, and Haiku 5.5) and Claude 4, GPT-6 (including GPT-6.1 Sol and Terra) and GPT-5.6 (OpenAI), GLM 4.7 (Z.ai), and Gemini 3 (including Deep Research)
5 skills · hooks
Four universal, opinionated skills for writing software: writing-code (API-consultation gate, dependency shape, orphaned-symbol sweep, footgun check, two-tier comment policy with a code-comment consistency gate), writing-tests (classicist behavior-first workflow with a dead-code stop that reports to the caller), writing-docs (single-owner surfaces, pointer-file discipline, anti-slop validation via the human-author:ai-slop-writing-fixer subagent), and sweeping-dead-code (a report-only sweep for unused code across a path, the repository, or a branch: a definition ledger, read-only runs of installed dead-code tools, reachability classification, and independent refutation subagents). Each skill is extendable at every step via Pre-Step-N / Post-Step-N positions and via recognized named configuration values; the plugin ships hooks that deliver a project's extension files (.claude/extensions/software-writer/) wrapped in a structural envelope.
4 skills · hooks
Consult OpenAI Codex for fresh analytical perspective — auto-escalation when stuck, on-demand second opinions, and web research. Uses the official codex-mcp-server with session management and GPT-5.2-codex.
1 skill · 1 command · 1 agent · 1 MCP server
Debug AI tooling behavior by analyzing output against source instructions and enabling honest self-diagnosis.
2 skills
Portable MCP read_file tool for reading local text files with offset and limit arguments.
1 MCP server · hooks
Enforces use of Claude Code native tools / native-build bfs & ugrep instead of bash equivalents (cat, find, grep, sed, echo). Adapts messages to the detected build: new mode (macOS/Linux native with bfs/ugrep), classic mode (Windows, or older builds with Glob/Grep tools), or pass-through when neither toolchain is available.
1 skill · hooks
Commit-message-writing skill for Conventional Commits. Mode detection (staged, squash, rewrite), a deterministic gather-script-driven workflow, anti-slop validation via the human-author:ai-slop-writing-fixer subagent, and validation mode. Extendable at every step via Pre-Step-N / Post-Step-N positions and via recognized named configuration values.
1 skill
One-time setup skill that provisions the hook plumbing and overlay content file needed to extend the commit-message-writer plugin's writing-commit-messages skill. Long plugin and skill names are intentional to prevent accidental invocation.
1 skill
Assess a single dependency update before adopting it. Detects the update and its release notes at runtime, then reports across three prongs: whether it requires code changes, what improvements (including testability) it enables, and whether a bug it fixes may still affect the application. Read-only end to end. Ecosystem, forge, and updater bot are detected from the host project, never assumed.
1 skill
Enforces Opus model for the Explore subagent. Maximum accuracy for codebase exploration.
hooks
Enforces Sonnet model for the Explore subagent. Prevents lossy compression from Haiku during codebase exploration.
hooks
Author content that reads like a human wrote it. Currently ships the ai-slop-writing-fixer subagent: receives prose, returns the prose with anti-slop violations corrected plus a structured change report.
1 agent
Enforces Opus model for the Plan subagent. Ensures maximum reasoning depth during plan mode.
hooks
Enforces Sonnet model for the Plan subagent. Ensures thorough architectural reasoning during plan mode.
hooks
Turn repository activity into platform-formatted posts. Currently ships the changelog-summarizing skill: walks committed history on main, groups commits by conventional-commit scope, synthesizes each group into a contextual paragraph, and dispatches the human-author:ai-slop-writing-fixer subagent before formatting Discord and Slack outputs.
1 skill
Prevents wasteful re-reads of unchanged files by tracking what was already read and blocking redundant Read tool calls. Tracks line ranges, detects content changes via hash, invalidates on Edit/Write, supports context decay thresholds, and allows retry on second attempt for deadlock escape.
hooks
One-time setup skill that explores a project's codebase, drafts project-specific extension content conversationally, and writes the per-skill extension files for the software-writer plugin's writing-code, writing-tests, writing-docs, and sweeping-dead-code skills (delivery on Claude Code ships with software-writer 3.0.0 or later; Codex delivery via AGENTS.override.md). Includes a re-sync mode that audits existing extension files for drift and migrates v1 hook-contexts setups. Long plugin and skill names are intentional to prevent accidental invocation.
1 skill
One-time setup skill that explores a project's gates, protected paths, conduct rules, recurring checkpoint types, and session topology, drafts the extension content conversationally, and writes the per-skill extension files for the work-orchestrator plugin (orchestrating-subagent-work and orchestrating-session-work; delivery ships with the work-orchestrator plugin, routing additions target the 5.0.0 duty definitions). Includes a re-sync mode that audits existing extension files for drift against the current project. Long plugin and skill names are intentional to prevent accidental invocation. Renamed from subagent-orchestrator-extension-setup
1 skill