claude

aoforge

Meta-prompting, context engineering, and spec-driven development system. 32 skills, 12 agents, stack packs for Flutter and web, wave-based parallelization, atomic commits, design-craft references, and persistent state across context resets.

0 on GitHubby AO Cyber Systemsv3.0.0MITupdated 27 days agodevelopment
/

Plugin aoforge from marketplace aocyber in AO-Cyber-Systems/aoforge-claude. Commands read from the repo's manifest — 27 days 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.

What it installs

Skills (31)

  • adopt

    Turn an existing repository into an AOForge project, unattended: map the code, infer PROJECT.md and STACK.md, scaffold config/STATE/ROADMAP, add the CLAUDE.md block, and make one recorded change on an aoforge/adopt branch. Never asks a question — uncertain inferences are written down with their conf

  • awareness

    Show cross-repo awareness: peer view (who's working on what in this repo) and org-wide progress (Product Roadmap). Renders both views by default. Triggers on: "who else is working on this", "what's in flight", "show org progress", "what are teammates working on". - Bash - Read

  • cleanup

    Archive old objective directories from completed milestones to reduce clutter. Moves completed work to the milestones archive — use only when explicitly requested. - AskUserQuestion

  • debug

    Investigate bugs using a structured approach that survives context resets. Tracks hypotheses, evidence, and progress across sessions. Use when the user reports a bug, error, or something not working as expected. Triggers on: "debug this", "something's broken", "fix this bug", "not working", "there's

  • decide

    Resolve a parked decision and resume autonomous execution. Use when you see a pending DECISION-NNN.md in .aoforge/decisions/pending/, when the user wants to choose an option for a blocked checkpoint:decision, or when you need to tell the executor which option to take. Triggers on: "resolve decision"

  • discuss-objective

    Capture implementation decisions for an objective before planning — lock in preferences so research and planning don't drift into assumptions. Use when the user wants to shape how an objective gets built before tasks are generated. Triggers on: "discuss objective", "shape the objective", "lock in pr

  • doctor

    Diagnose and safely repair AOForge environment problems: a stale runtime mirror, runtime state committed or left untracked inside a repo, pending migrations, stale markers, guard state, awareness cache and backups, hook registry drift, and out-of-date model ids. Read-only by default; `--fix` applies

  • execute-objective

    Execute all planned tasks for an objective, running independent tasks in parallel for speed. Use when the user wants to run or execute an already-planned objective. Triggers on: "execute objective", "run objective", "run the jobs", "run the planned objective", "execute the plan" - Read - Write - Edi

  • flow

    Orchestrate a multi-step AOForge workflow by chaining skills. Use when the user wants to invoke a sequence of skills as one ask (e.g., "build and sync to github", "research, plan, then build", "ship and announce"). Triggers on: "ship X to Y", "build and X", "plan and X", "X then Y", "in one go", "as

  • gh-sync

    Operate the GitHub store, where GitHub is the system of record once `github.store` is on: migrate a project onto it (dry run first, then explicit approval), show store status, flush the outbox, pull the cache, set the repository up, generate release notes. With the store off, mirror objectives to Gi

  • handoff

    Hand off a TTY-required or shell-env-dependent command to the user's shell. Use for auth flows (gh auth login, doctl auth init, npm login) or shell-init commands (nvm/mise/conda activate, direnv). Non-disruptive when aoforge-watch is running. Triggers on: "auth init", "log in to", "needs my password

  • help

    Show available AOForge commands and usage guide. Use when the user asks about AOForge capabilities, available commands, or how to use the system. Triggers on: "what can you do?", "how do I use AOForge?", "show commands", "aoforge help", "what commands are available?

  • initiatives

    Manage strategic initiative context — sync GitHub Epics to disk, list cached initiatives, or show a single initiative body. Planner reads these at plan time. Triggers on: "sync initiatives", "refresh initiatives", "show initiative", "what initiatives are loaded". - Bash - Read

  • list-objective-assumptions

    See what Claude plans to do for an objective before it starts, so you can course-correct early. Shows the intended approach without creating any files. - Read - Bash - Grep - Glob - AskUserQuestion

  • map-codebase

    Analyze an existing codebase to understand its stack, architecture, conventions, and concerns before starting new work. Use when the user wants to understand, analyze, or map an existing codebase. Triggers on: "understand this codebase", "map the code", "analyze architecture", "what does this codeba

  • micro

    Sub-30-LOC, single-file changes. The cheapest AOForge path (~2k tokens). Use for typo fixes, single-line bug fixes, prop renames, dependency bumps, missing semicolons. Triggers on: "fix typo", "rename X to Y", "1-line fix", "single-file change", "tiny", "trivial" - Read - Write - Edit - Bash - AskUs

  • milestone

    Manage milestones: start a new one, audit a finished one, complete it, or plan gap-closure objectives. Subcommand-style: /aoforge:milestone new | audit | complete | gaps Use when explicitly requested. - Read - Write - Bash - Task - AskUserQuestion - EnterPlanMode - Glob - Grep

  • new-project

    Set up a new project from scratch — asks what you're building, researches the domain, defines requirements, and creates a development roadmap. Use when the user wants to start a new project or initialize AOForge for the first time. Triggers on: "start a new project", "initialize project", "let's bui

  • objective

    Add or remove an objective from the current milestone roadmap. Subcommand-style: /aoforge:objective add | remove Use when explicitly requested. Note: 'insert' (decimal objectives) was removed in v1.2 — use 'add' instead. - Read - Write - Bash - Glob - AskUserQuestion

  • plan-objective

    Create a detailed execution plan for an objective, breaking it into concrete tasks with success criteria. Use when the user wants to plan an objective, create execution plans, or prepare for building. Triggers on: "plan objective", "create plans", "plan the next objective", "let's plan", "prepare ob

  • quick

    Small features (single executor, no planner, no verifier) — between micro (1-line) and build (multi-subsystem). Cutoff: <5 files, <200 LOC, no new abstractions. Use when the change is too big for /aoforge:micro but doesn't warrant full /aoforge:build planning. Triggers on: "small change", "small fea

  • research-objective

    Research how to build something before planning it — discovers best practices, architecture patterns, and pitfalls for the domain. Use when the user wants to investigate, research, or explore options before planning an objective. Triggers on: "research objective", "investigate before planning", "loo

  • security-audit

    Scan the codebase for security vulnerabilities — checks for secrets, auth flaws, dependency risks, and OWASP Top 10 issues. Standalone — works without project setup. Covers secrets, auth, dependencies, and code-level vulnerabilities. Triggers on: "security audit", "scan for vulnerabilities", "check

  • set-profile

    Switch between quality, balanced, and budget model profiles to control cost and capability. Use when the user wants to change the AI model tier for AOForge agents. Triggers on: "change profile", "switch to quality", "switch to balanced", "switch to budget", "set profile" - Read - Write - Bash

  • settings

    Configure which agents run, which AI models they use, and how the workflow behaves. Use when the user wants to change AOForge settings or configure workflow behavior. Triggers on: "change settings", "configure AOForge", "update settings", "workflow settings" - Read - Write - Bash - AskUserQuestion

  • status

    Consolidated status/resume/pause/health — `/aoforge:status [resume|pause|check]`. Default: show progress + route to next action. Subcommands: check (integrity), pause (save context), resume (restore context). Both flag and bare forms accepted. Triggers on: "where are we?", "what's next?", "save my p

  • sync-roadmap

    Reconcile ROADMAP.md checkbox state against on-disk SUMMARY.md presence. Default: silently corrects drift; --dry-run previews; --interactive prompts per change. Triggers on: "sync roadmap", "reconcile roadmap", "fix roadmap drift", "is the roadmap accurate". - Bash - Read

  • todo

    Manage todos: capture an idea/task or view the morning standup across local + GitHub + peer sources. Subcommand-style: /aoforge:todo add | list Use when the user wants to save something for later, note an idea, or get a "what should I work on?" view. Triggers on: "remember to", "add a todo", "save t

  • tui

    Open the program-aware TUI viewer — read-only terminal UI showing parallel sessions, org tree, and active initiatives in three stacked panels. tmux-safe; reflows narrow terminals. Triggers on: "open tui", "show tui", "what's running across sessions", "show org tree". - Bash - Read

  • verify-work

    Test what was built by walking through expected behavior and checking it matches reality. Use when the user wants to test, verify, or validate what was built in an objective. Triggers on: "test what we built", "verify objective", "check the work", "UAT", "does it work?", "let's test", "validate the

  • workstreams

    Run independent objectives in parallel using git worktrees, then merge results back. Subcommand-style: /aoforge:workstreams setup | status | merge | run Advanced parallel execution — use only when explicitly requested. - Read - Write - Edit - Glob - Grep - Bash - Task - AskUserQuestion

Subagents (12)

  • codebase-mapper

    Analyzes a codebase from a specific angle (stack, architecture, quality, or concerns) and writes structured findings.

  • debugger

    Investigates bugs using a structured scientific method with persistent session state across context resets.

  • executor

    Executes planned tasks with atomic git commits, handles deviations, and manages checkpoints during builds.

  • integration-checker

    Verifies that separately-built features connect properly and end-to-end user workflows actually work.

  • job-checker

    Reviews execution plans before they run to verify they will actually achieve the objective goal.

  • objective-researcher

    Researches how to implement an objective — discovers best practices, patterns, and pitfalls before planning begins.

  • planner

    Creates detailed execution plans for objectives with task breakdown, dependency ordering, and built-in quality checks.

  • project-researcher

    Researches the domain ecosystem for a new project — stack options, architecture patterns, features, and common pitfalls.

  • research-synthesizer

    Combines findings from multiple parallel research agents into a unified summary for roadmap creation.

  • roadmapper

    Creates project roadmaps by breaking requirements into ordered objectives with success criteria and dependency mapping.

  • security-auditor

    Scans codebase for security vulnerabilities in a specific domain: secrets, auth flows, or dependency risks.

  • verifier

    Verifies that built code actually achieves the objective goal, not just that tasks were completed.

Hooks (19)

  • SessionStart

    node ${CLAUDE_PLUGIN_ROOT}/hooks/sync-runtime.js

  • SessionStart

    node ${CLAUDE_PLUGIN_ROOT}/hooks/upgrade-project.js

  • SessionStart

    node ${CLAUDE_PLUGIN_ROOT}/hooks/awareness-cache-populate.js

  • SessionStart

    node ${CLAUDE_PLUGIN_ROOT}/hooks/classify-session.js

  • SessionStart

    node ${CLAUDE_PLUGIN_ROOT}/hooks/coexistence-guard.js

  • Stop

    node ${CLAUDE_PLUGIN_ROOT}/hooks/verify-completion.js

  • Stop

    node ${CLAUDE_PLUGIN_ROOT}/hooks/auto-continue.js

  • Stop

    node ${CLAUDE_PLUGIN_ROOT}/hooks/gh-flush.js

  • Stop

    node ${CLAUDE_PLUGIN_ROOT}/hooks/todo-sync.js

  • SubagentStop

    node ${CLAUDE_PLUGIN_ROOT}/hooks/verify-commits.js

  • SubagentStop

    node ${CLAUDE_PLUGIN_ROOT}/hooks/gate-executor-stop.js

  • UserPromptSubmit

    node ${CLAUDE_PLUGIN_ROOT}/hooks/route-intent.js

  • UserPromptSubmit

    node ${CLAUDE_PLUGIN_ROOT}/hooks/route-results.js

  • UserPromptExpansion

    node ${CLAUDE_PLUGIN_ROOT}/hooks/gate-skill-requires.js

  • PreToolUse

    node ${CLAUDE_PLUGIN_ROOT}/hooks/pre-bash.js

  • PreToolUse

    node ${CLAUDE_PLUGIN_ROOT}/hooks/gate-edits.js

  • PreToolUse

    node ${CLAUDE_PLUGIN_ROOT}/hooks/gate-skill-requires.js

  • PreToolUse

    node ${CLAUDE_PLUGIN_ROOT}/hooks/guard-no-progress.js

  • PostToolUse

    node ${CLAUDE_PLUGIN_ROOT}/hooks/gh-flush.js

View source on GitHub

More from AO-Cyber-Systems/aoforge-claude

All 9 plugins →

devflow

claude

DevFlow is now AOForge: install aoforge@aocyber. This final release forwards /devflow: commands and is removed in the next release.

31 skills · hooks

0

AOForge stack pack for Flutter and Dart: UI verification gates, the visual-eval judge, the design critic and Flutter-aware planning. Needs aoforge.

2 skills · 1 agent · hooks

0

Enforce monorepo standards: block compiled binaries from git via pre-commit hook, validate layout against root CLAUDE.md, scaffold new product monorepos (go/, flutter/, admin/, proto/) with per-area CLAUDE.md and path-filtered CI.

2 skills · hooks

0

AOForge stack pack for web UIs: the verifier's Playwright browser drive, run by a dedicated agent. Needs aoforge and the Playwright plugin.

1 agent · hooks

0

AI media and gateway management MCP servers. 45 tools: image generation, vision analysis, TTS, transcription, spend analytics, API key management, guardrails, models, users, teams, orgs, budgets, and config.

2 MCP servers

0

Build, review, and visually inspect websites with Hugo and Tailwind CSS. Brand-per-project design system with dpcco and aocyber presets. Includes brand builder skill.

2 skills

0

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

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

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

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

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Maintain aoforge?

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 plugins9 plugins