Skill Claude CodeCodex
Answer, plan, ratify, or autonomously implement clisbot architecture work from repository evidence. Use when a request may change channel, agent, session, runner, auth, configuration, control, persistence, process, API, UI, integration, ownership, lifecycle, or contract boundaries; when the user asks how clisbot…
Skill Claude CodeCodex
Plan, decide, or review names in clisbot with repository evidence for domain terms, APIs, CLI commands, folders, files, functions, variables, classes, types, events, config keys, persisted fields, channel concepts, runner capabilities, UI concepts, and abstractions. Use when the user invokes naming-expert, asks to…
Instructions file CodexOpenCode
Instructions for longbkit/clisbot, covering agents.md, how to code, scope, first read order and documentation precedence.
Instructions file
Instructions for longbkit/clisbot, covering agents.md, scope, first read order, documentation precedence and repo map.
Agent
Historical audit with a shipped follow-up.
Agent
The agents layer owns inbound attachment placement inside the agent workspace.
Agent
This document defines agent-scoped command dispatch inside a conversation.
Agent
This document defines the current session model used by clisbot.
Agent
This note holds the validation detail behind the task doc.
Agent
Agent "2026-05-16-hermes-agent-self-evolution" from longbkit/clisbot, covering hermes agent self-evolution research, executive take, what is implemented vs planned, implemented in hermes-agent and implemented in hermes-agent-self-evolution.
Agent
Make the lifecycle and state model in the agents layer reliable without leaking runner-specific mechanics into it.
Agent
Extend agent-scoped bash commands beyond the one default reusable shell surface.
Agent
Close the remaining gap between clisbot session behavior and OpenClaw's broader routing and session-management model.
Agent
Add session-scoped follow-up policy, configurable TTL, and a runtime control API so agents can change conversation behavior dynamically when the user asks.
Agent
Agent "2026-04-06-agent-workspace-attachments" from longbkit/clisbot, covering agent workspace attachments, status, priority, why and scope.
Agent
Evaluate whether broader launch should include a stronger compatibility layer for native CLI slash commands, plus explicit override and customization surfaces when commands conflict.
Agent
Expand the agents layer so clisbot can act less like a prompt-forwarding bot and more like a capable work agent.
Agent
Add a first-class queue creation/control surface similar to managed loops, but for one-shot follow-up prompts in the same routed session.
Agent
Add a local clisbot audio CLI surface for two-way audio conversion.
Agent
Agent "2026-05-02-live-session-id-runtime-truth-and-memory-registry" from longbkit/clisbot, covering live session id runtime truth and memory registry, status, priority, summary and why.
Skill Claude CodeCodex
Queue-first continuation and review workflow for clisbot queues. Use when work needs deliberate follow-up against early stopping, shallow passes, prompt echoing, history leaking, duplicate files/functions/sections, naming drift, DRY/KISS regressions, missing docs/tests, or bad fallback behavior.
Skill Claude CodeCodex
Release clisbot safely to npm and GitHub. Use when Codex is asked to prepare, validate, bump, publish, tag, or document a clisbot beta release, next beta release, or official stable/latest release, including release notes, migration notes, GitHub release notes, npm dist-tags, and post-publish verification.
Skill Claude CodeCodex
A skill for opening diffs in difit for user review, or for reviewing a specific diff or PR first and preloading findings into difit as inline comments. Use it after code changes, for commit or branch comparisons, or when a human-readable web diff with anchored comments is the best review surface.