core

Plugin core in b-open-io/prompts. Commands read from the repo's manifest — today.

Skills (15)

• auth-md

  Implement or review the experimental WorkOS auth.md v0.6.0 agent-identity proposal. Use for "implement auth.md", "add agent registration", "design delegated agent signup", "support service_auth", "mint or verify an ID-JAG", "build an agent identity provider", or agent-facing OAuth consent, claims, a

• check-version

  Compare installed plugin versions against GitHub to confirm skills and agents are current. Use at session start, for "is everything up to date", "are my plugins up to date", "are our plugins current", "check for plugin updates", "is anything stale", "am I on the latest version", "did that plugin upd

• codex-agent-setup

  Generate and install Codex agent adapters so plugin personas are invocable from the Codex CLI. Use for "set up codex agents", "install the codex adapters", "make these agents work in Codex", or when a persona is missing from a Codex session. author: b-open-io version: "1.0.3" codex: disable-model-in

• confess

  Proactive self-audit covering incomplete changes, untested assumptions, pattern violations, buried concerns, and cleanup debt. Invoke before ending a session, marking a task done, or saying "complete", and when the user asks "are you sure?", "did you miss anything?", "anything else?", or "audit your

• front-desk

  Route to the right agent, skill, or service provider. Use for "who handles X?", "what agents are available?", "team roster", "what skills are available?", "where do I find skill X?", "who should I talk to about Z?", "install in Grok Bot", "stand up the roster", or "Grok Bot teammates". Also covers a

• hammertime

  This skill should be used when the user mentions a behavioral rule they want enforced, says "always do X", "never do Y", "stop doing Z", "from now on", asks about HammerTime rules, wants to create a stop hook rule, mentions behavioral guardrails, or wants to understand how the HammerTime stop hook s

• hook-manager

  List, enable, or disable individual core hooks and check their prerequisites. Use for "list hooks", "enable a hook", "disable a hook", "hook setup", "hooks config", or a [BOPEN-HOOKS-SETUP] directive. For the full harness view, use setup.

• humanize

  This skill should be used for human-facing prose — emails, docs, reports, posts, release notes, and commit messages — when the user asks to "humanize", "make this sound less AI", "de-AI this", "this sounds like ChatGPT", or "edit this". This skill should also be used when the user asks to "humanize

• linear-planning

  This skill should be used when the user wants to plan a project, feature, or bug fix using Linear as the agent control plane. Use when the user says "plan this in Linear", "create Linear tickets", "break this down into tasks", "push to Linear", "set up our board for this feature", or wants to turn a

• reinforce-skills

  Inject compressed SKILL-MAP and AGENT-MAP directive blocks into CLAUDE.md so skill names and agent IDs survive a long session. Use when modifying a CLAUDE.md, when adding a skill or agent to a plugin, or for "update the skill map", "register this agent", "skills keep getting forgotten", "sync skills

• remind

  Search and recall previous Claude Code sessions. Use for "remember when we...", "what did we do about...", "find that conversation where...", "when did I last work on...", "what was that command we used for...", or any reference to prior work absent from the current session, including vague ones lik

• restraint

  YAGNI with a governor: write the least code that is still the right code. This skill should be used on any coding task — writing, adding, refactoring, fixing, reviewing, designing code, or choosing libraries and dependencies — and whenever the user says "restraint", "/restraint", "don't over-build",

• runtime-context

  Use when the user asks what runtime or host is active, which capabilities are available, or how behavior should adapt across Claude Code, Codex, Grok, OpenCode, a sandbox, or local development. Reports observed capabilities without inferring tools from host identity.

• setup

  Audit which bOpen plugins, CLIs, env keys, third-party skills, agents, and hooks are installed across the harness, then emit a runtime-tailored instruction plan with optional user-triggered installation of selected dependencies. Use for "bopen setup", "setup ui", "harness install", "audit my setup",

• visual-wayfinder

  Generate a navigable visual map of a codebase or system for orientation. Use when the user asks to "map this codebase", "show me how this fits together", "give me a tour", or needs a visual orientation artifact before working in unfamiliar code.

Slash commands (14)

• /core:bug-hunt

  Adversarial bug hunt with 3 isolated agents — Hunter finds bugs, Skeptic challenges them, Referee gives final verdicts

• /core:diagnose

  Fan out 3-5 agents to investigate a bug from every angle simultaneously

• /core:factory-init

  Interactively design and scaffold an autonomous agent loop in this project (goal, gate, state, stop conditions, heartbeat, human-readable GitHub PRs)

• /core:hammertime

  Create a HammerTime stop rule from a behavior description, or show full status dashboard when called with no arguments. See also /hammertime:manage for interactive rule management

• /core:hammertime:manage

  Interactive HammerTime rule management — enable, disable, remove, or edit rules with guided prompts

• /core:hammertime:start

  Resume HammerTime — re-enables the stop hook after /hammertime:stop

• /core:hammertime:status

  Show HammerTime status dashboard — rules, debug log, hook health

• /core:hammertime:stop

  Pause HammerTime — disables the stop hook until resumed with /hammertime:start

• /core:impact

  Map the full blast radius before changing a file or function — importers, tests, CI, docs, owners

• /core:prime

  Context warm-up — loads git state, plugin inventory, and project conventions before starting work

• /core:question

  Read-only Q&A mode — answers questions about the codebase without making any changes

• /core:review-wave

  4 specialized reviewers examine changes simultaneously — security, perf, correctness, style

• /core:utils:context

  Print a concise repository context snapshot for agents (git, pkg, dirs)

• /core:visual-review

  Turn a PR, branch, commit, or diff into a plain-language visual review with grounded diagrams and decision questionnaires

Subagents (4)

• community-manager

  BSV and 1Sat Ordinals community agent for the OneSat Discord. Use this agent when users ask "what are 1Sat Ordinals", "mint this as an ordinal", "check my GM streak", "how's my trust score", or want trivia polls, airdrop history, or BSV20/BSV21 token help. Not for building production ordinals infras

• customer-support

  Slack customer support for the org's products and services. Use this agent when someone needs a support channel watched, an inbound Slack question triaged, a reply drafted, or a customer issue escalated to the right specialist. Covers periodic channel watch, triage, and draft replies. Not for OneSat

• front-desk

  Organization front desk and directory service. Use this agent when users ask "who handles X", "what agents are available", "who's working on Z", "what services do we use", how to install the roster on Claude Code, Codex, Grok Build, or Grok Bot, or need routing to the right specialist. Routes SOC 2

• project-manager

  Linear project planning agent. Use this agent when the user asks to "plan this in Linear", "create tickets for this", "break this into issues", "set up our board", "what should we build next", or asks how linear-sync and the linear-planning skill fit together. Turns specs, descriptions, or a codebas

Hooks (7)

• SessionStart

  BOPEN_HOOK_SCRIPT="${GROK_PLUGIN_ROOT}/hooks/session-context.sh"; if [ ! -f "$BOPEN_HOOK_SCRIPT" ]; then BOPEN_HOOK_SCRIPT="${CLAUDE_PLUGIN_ROOT}/hooks/session-context.sh"; fi; if [ ! -f "$BOPEN_HOOK_

• SessionStart

  BOPEN_HOOK_SCRIPT="${GROK_PLUGIN_ROOT}/hooks/repo-freshness.sh"; if [ ! -f "$BOPEN_HOOK_SCRIPT" ]; then BOPEN_HOOK_SCRIPT="${CLAUDE_PLUGIN_ROOT}/hooks/repo-freshness.sh"; fi; if [ ! -f "$BOPEN_HOOK_SC

• UserPromptSubmit

  BOPEN_HOOK_SCRIPT="${GROK_PLUGIN_ROOT}/hooks/browser-intent.sh"; if [ ! -f "$BOPEN_HOOK_SCRIPT" ]; then BOPEN_HOOK_SCRIPT="${CLAUDE_PLUGIN_ROOT}/hooks/browser-intent.sh"; fi; if [ ! -f "$BOPEN_HOOK_SC

• PreToolUse

  BOPEN_HOOK_SCRIPT="${GROK_PLUGIN_ROOT}/hooks/pretooluse-bash.sh"; if [ ! -f "$BOPEN_HOOK_SCRIPT" ]; then BOPEN_HOOK_SCRIPT="${CLAUDE_PLUGIN_ROOT}/hooks/pretooluse-bash.sh"; fi; if [ ! -f "$BOPEN_HOOK_

• PreToolUse

  BOPEN_HOOK_SCRIPT="${GROK_PLUGIN_ROOT}/hooks/damage-control.sh"; if [ ! -f "$BOPEN_HOOK_SCRIPT" ]; then BOPEN_HOOK_SCRIPT="${CLAUDE_PLUGIN_ROOT}/hooks/damage-control.sh"; fi; if [ ! -f "$BOPEN_HOOK_SC

• PreToolUse

  BOPEN_HOOK_SCRIPT="${GROK_PLUGIN_ROOT}/hooks/roster-guard.sh"; if [ ! -f "$BOPEN_HOOK_SCRIPT" ]; then BOPEN_HOOK_SCRIPT="${CLAUDE_PLUGIN_ROOT}/hooks/roster-guard.sh"; fi; if [ ! -f "$BOPEN_HOOK_SCRIPT

• Stop

  BOPEN_HOOK_SCRIPT="${GROK_PLUGIN_ROOT}/hooks/hammertime.py"; if [ ! -f "$BOPEN_HOOK_SCRIPT" ]; then BOPEN_HOOK_SCRIPT="${CLAUDE_PLUGIN_ROOT}/hooks/hammertime.py"; fi; if [ ! -f "$BOPEN_HOOK_SCRIPT" ];

Similar plugins