claude-mem
claudecodexPersistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
cairn 2.0 — converged work management: tracker-truth planning, provenance-checked memory, and a per-verb /cairn:<verb> surface, backed by a typed MCP server.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin cairn in eventually-consistent-code-org/cairn2. Commands read from the repo's manifest — 3 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
mcp-v2-migrationUse when executing the MCP SDK v1→v2 migration (phase 12, native grain) — validated codemod path, the zod 3→4 fix inventory, and the test-triage method proven by probe-6651a387's full dress rehearsal.
native-task-hook-mirrorUse when building or planning the native-Tasks→tracker mirror (phase 12, native grain) — validated hook behavior, payload shapes, and the three design constraints proven by probe-1733c5c9.
cairn-memoryUse when a repo has cairn.json and the cairn MCP tools (mem_*) are available — the cairn 2.0 memory lifecycle. Owns the distill-then-drop policy (what deserves a durable card vs. disposable index), scoped recall conventions, staleness handling, and the capacity-guard advisory.
cairn-planningUse when a repo has cairn.json and the cairn MCP tools (plan_*, issue_*) are available — the cairn 2.0 planning lifecycle. Owns the depth dial (quick/standard/deep), the model-routing rubric for agent fan-out, artifact conventions under .cairn/plans/, and the precedence rule (git plan docs win over
cairn-trailheadUse when routing /cairn:<verb> invocations — owns the verb registry and shared execution rules for every cairn subroutine.
/cairn:auditCross-phase quality audits — uat/milestone/security[--surface]/ui/eval/validation/tests/plans/docs/simplify/memory/debt/sweep (whole-project rescan) (/cairn:help)
/cairn:autoChained hands-off execution of remaining phases (opt-in) (/cairn:help)
/cairn:backtrackSafe git undo by phase/plan manifest — reverts only (/cairn:help)
/cairn:basecampMulti-project workspaces — dispatch board, focus, parallel workstreams (/cairn:help)
/cairn:briefOnboarding briefing from cards + plans (/cairn:help)
/cairn:distillShip-time synthesis — plans + cards → public-safe docs/ (/cairn:help)
/cairn:doFreeform smart router — classify intent, dispatch the right verb (/cairn:help)
/cairn:docsPublish repo docs to the configured docs connector (Confluence or Docusaurus) — landing page + page tree (/cairn:help)
/cairn:draftMulti-variant mockups on a shared theme (/cairn:help)
/cairn:fastTrivial inline change — one issue, ≤3 files, atomic commit (/cairn:help)
/cairn:helpRender this verb reference (/cairn:help)
/cairn:importReverse-mirror a tracker epic/milestone/list into plan artifacts (/cairn:help)
/cairn:mapProject knowledge graph — build, query, diff, status (/cairn:help)
/cairn:markZero-friction capture — backlog/seed to tracker, note to memory (/cairn:help)
/cairn:medicPlanning-dir health, repair, and workflow forensics (/cairn:help)
/cairn:newStart here — new project: interview, plan artifacts, tracker mirror, issues (/cairn:help)
/cairn:outlookPortfolio board — every cairn project on this machine, staleness-flagged, cost rollup (/cairn:help)
/cairn:peersConvene external AI CLIs as reviewers — convergence with adversarial judgment (/cairn:help)
/cairn:planPlan a phase — research per depth, write PLAN.md, reconcile tracker (/cairn:help)
/cairn:probeRisk-ordered throwaway spike experiments with verdicts (/cairn:help)
/cairn:profileDeveloper profile — calibrates how cairn talks to you (/cairn:help)
/cairn:recallSearch memory, scoped to the active context, with staleness flags (/cairn:help)
/cairn:rememberStore a durable fact as a memory card (or bulk into the index) (/cairn:help)
/cairn:resyncDetect out-of-band commits; refresh plan context (/cairn:help)
/cairn:retroRetrospective — provenance-backed lesson cards, confidence re-grading (/cairn:help)
/cairn:reviewFive-axis code review of a diff, branch, or phase (/cairn:help)
/cairn:routeRe-route the roadmap — insert/remove/edit phases (/cairn:help)
/cairn:scoutResearch a phase only — resumable RESEARCH.md checkpoints (/cairn:help)
/cairn:shipGate on drift-clean + no open issues in verified phases, then push (/cairn:help)
/cairn:statusOne view — phases, issue states, drift, unplanned work (/cairn:help)
/cairn:summitComplete the milestone — verify gate, tracker close/release, archive, tag (/cairn:help)
/cairn:surveyProject-wide research — findings, then discussed roadmap changes (/cairn:help)
/cairn:threadPersistent context threads that survive /clear (/cairn:help)
/cairn:tracePersistent debugging session — evidence→hypothesis→test, tracker-mirrored (/cairn:help)
/cairn:triageOpen-issue sweep against project conventions — report by default, --apply for the safe subset (/cairn:help)
/cairn:tuneConfigure cairn.json — models, continuity, leak guard (/cairn:help)
/cairn:verifyGoal-backward phase check, drift clean, write VERIFICATION.md (/cairn:help)
/cairn:waypointPause/resume session continuity (/cairn:help)
/cairn:workExecute a phase — claim issues, do the work, close on verified done (/cairn:help)
cairn-designerTurns a design question into a decided direction with artifacts — wireframes, design tokens, coded prototypes — inside a cairn draft session. Dispatched by the `draft` verb for non-trivial design questions; the verb keeps session lifecycle and tracker mirror, this agent runs the design work under it
cairn-uatProves shipped flows meet requirements, platform-aware — walks each flow as a user on a named viewport matrix, sweeps requirement traceability, and hands off fidelity divergence to `audit ui`. Dispatched by `audit uat` (and `audit ui` for fidelity) as the acceptance specialist.
cairnruns: node ${CLAUDE_PLUGIN_ROOT}/server/dist/index.js
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pretooluse-leakguard.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pretooluse-runguard.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pretooluse-harnessguard.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pretooluse-writeguard.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/posttooluse-breadcrumb.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/posttooluse-observe.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/posttooluse-loopcheck.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/posttooluse-observe.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/stop-costtracker.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/sessionstart-continuity.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/notification-pause.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/notification-pause.mjs"
Problems found in this repo's manifests
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents
7 skills · 7 commands · 2 agents · hooks
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 1 MCP server · hooks
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.