Agent
QA lens agent: probes the RUNNING product — web UI via Playwright MCP, API via curl/HTTP — through ONE assigned lens (user-flow · edge-state · honesty · contract · ux-critique) and returns STRUCTURED FINDINGS with repro steps + evidence. Observation-only: it never decides, never fixes, never edits files, never clicks…
Agent
Read-only fact-gatherer (the model split: the main session designs; recon gathers — breadth over depth). Use for: mapping a codebase surface before a design, input-availability tables, verifying a doc claim against code, sweeping many files for a fact, external fresh-checks against official sources. Returns RAW FACTS…
Hook
Runs when a session starts on startup, clear, resume, compact and fork, executing session-start.py via python3. From awrshift/agent-memory-kit.
Hook
Runs before the agent uses a tool for Edit and Write tool calls, executing protect-tests.py via python3. From awrshift/agent-memory-kit.
Hook
Runs before the context is compacted, executing pre-compact.sh via bash. From awrshift/agent-memory-kit.
Hook
Runs when a session ends, executing session-end.sh via bash. From awrshift/agent-memory-kit.
Skill Claude CodeCodex
End-of-session ritual — audit today's patterns against accumulated memory, propose promotions, refresh MEMORY.md, and write the session handoff. Use when the user says "/memory-kit:close-session", "закрой сессию", "закрываем", "we're done for today", "wrap up".
Skill Claude CodeCodex
Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, stacked chronicle blocks, stale entries. Produces a move plan as a table for approval, then executes the approved moves atomically. Use when the SessionStart hook reports a tripped…
Skill Claude CodeCodex
Run a multi-lens agent QA sweep of the RUNNING product: spawn qa agents (one per lens — user-flow · edge-state · honesty · contract · ux-critique), collect their structured findings, integrator-verify the load-bearing ones, and land verified findings as backlog tickets + a run record in the project's qa/ folder. Use…
Skill Claude CodeCodex
Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test', 'devil's advocate', 'run a full review', 'this is important', 'high-stakes', 'help me choose between', 'critique…
Skill Claude CodeCodex
End-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then run independent reviewers in parallel — an isolated code-reader (the idea-validator agent) that reads the ACTUAL files and web-checks technology currency, plus an external-family model if you have one …
Skill Claude CodeCodex
Adopt the Memory Kit in THIS repository — scaffold the memory layers, decide how the kit coexists with Claude Code's native auto memory, and install safe permission rails. Use when the user says "/memory-kit:setup", "set up the memory kit", "adopt the kit here", "настрой кит", or when a session starts in a repo where…
Skill Claude CodeCodex
Periodic evidence-based self-audit of the whole agent system — the orchestrator, its docs/SSOTs, rules, memory, subagents, tools, infra and the work it claims to have delivered — followed by immediate cheap-safe fixes and a ranked backlog. Use when the user says 'аудит системы', 'проверь себя', 'самопроверка', 'system…
Skill Claude CodeCodex
Interactive walkthrough of the Memory Kit system using the user's actual project files. Use when the user says "/memory-kit:tour", "give me a tour", "покажи как это работает", or right after /memory-kit:setup.
Plugin Claude Code
Plugin marketplace listing 1 plugin: telegram.
Skill Claude CodeCodex
The only Telegram skill your AI agent needs. Read messages, parse channels, download and transcribe voice notes — all via Telethon user API. One session file, zero bots. Use when user says 'read telegram', 'check saved messages', 'fetch from telegram', 'parse channel', 'transcribe voice', 'telegram search', 'check my…
Plugin Claude Code
Plugin marketplace listing 1 plugin: claude-friends.
Plugin Claude Code
Claude asks AIs from other families before the calls that matter: Gemini, an isolated second Claude with no memory of the conversation, optionally GPT. Three review styles, picked from what you type. CLI only, no MCP server.
Agent
Isolated Claude Opus that critiques ideas, designs, patterns, hypotheses, or plans without context from the parent conversation. Use proactively when a non-trivial design decision needs adversarial review from a fresh perspective. Pair with Gemini second-opinion (parallel call) for two independent opinions from…
Skill Claude CodeCodex
Ask AIs from other families to review something before you commit to it. User-triggered, never automatic. Fires when the user signals uncertainty or asks for another perspective: 'ask a friend', 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test this', 'critique this', 'devil's…
MCP server Claude CodeCodexCursor
Open-source identity engine for AI agents. Deterministic personality from celestial mechanics. Runs locally from the clawclaw-soul Python package.