memory-kit

Plugin memory-kit from marketplace memory-kit in awrshift/agent-memory-kit. Commands read from the repo's manifest — today.

Skills (10)

• close-session

  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".

• code-sync

  Reconcile the project's documents with what the code now shows, after a merge or at the end of a build: spec statuses (building → done only with a named gate, or → stale with the reason), assumed specs owed ratification, the project README map and its Last verified date. Surgical edits only. Use whe

• document

  Write the human-facing prose about a change — PR body · changelog entry · release note · postmortem — and put it in the right file. Use when the user says "write the PR", "PR description", "PR body", "changelog", "changelog entry", "release note", "release notes", "postmortem", "write up the inciden

• memory-audit

  Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, session-headed chronicle blocks, restated rules, copied numbers, stale entries. Produces a move plan as a table for approval, then executes the approved moves atomic

• qa-sweep

  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 projec

• second-opinion

  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

• session-review

  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 mode

• setup

  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 (`/memory-kit:setup rails` re-runs only the rails step on an adopted repo; `/memory-kit:setup adopt` after an upgrade sorts the k

• system-audit

  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', 'сам

• tour

  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.

Subagents (4)

• executor

  Builder to an ALREADY-DECIDED spec (the model split: the main session designs; the executor builds). Use for: building a designed slice/chunk, test writing, mechanical refactors with an objective gate (typecheck, test suites, byte-replay). The spec — normally a file at `projects/<name>/plans/YYYY-MM

• idea-validator

  Isolated Claude instance 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 an external-family model (parallel call) when you have

• qa

  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 f

• recon

  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.

Hooks (12)

• SessionStart

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.py" --part 1

• SessionStart

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.py" --part 2

• SessionStart

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.py" --part 3

• SessionStart

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.py" --part 4

• SessionStart

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.py" --part 5

• SessionStart

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.py" --part 6

• PreToolUse

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/protect-tests.py"

• PreToolUse

  python3 -c 'import sys; sys.exit(sys.version_info < (3,9))' >/dev/null 2>&1 || exit 0; python3 "${CLAUDE_PLUGIN_ROOT}/hooks/guard-git.py"

• PreToolUse

  python3 -c 'import sys; sys.exit(sys.version_info < (3,9))' >/dev/null 2>&1 || exit 0; python3 "${CLAUDE_PLUGIN_ROOT}/hooks/guard-zsh-split.py"

• PreToolUse

  python3 -c 'import sys; sys.exit(sys.version_info < (3,9))' >/dev/null 2>&1 || exit 0; python3 "${CLAUDE_PLUGIN_ROOT}/hooks/guard-secrets.py"

• PreCompact

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/pre-compact.sh"

• SessionEnd

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-end.sh"

Similar plugins