thrum

Plugin thrum from marketplace thrum in leonletto/thrum-pro. Commands read from the repo's manifest — 13 days ago.

Skills (68)

• adversarial-critique

  Use when an implementer is blocked mid-work by a design flaw, contradiction, or unforeseen fork with 2-3 ways to resolve it - produces a defended pick that unblocks the work and leaves an audit trail so the decision can be revisited if it later proves wrong

• agent-messaging-protocol

  Use when forwarding or relaying information between parties, routing an owner answer, carrying a decision or request through an intermediary, summarizing another author's message, or adding interpretation to someone else's words.

• brainstorm-queue-aware

  Use when running as a brainstormer that a Brainstorm Steward is managing — redirect every Q-by-Q question to the Steward as a NEED message and block for the ANSWER instead of asking the human directly. Fires when your briefing names a steward.

• brainstorm-steward

  Use when running as the Brainstorm Steward - a persistent watcher that manages a roster of brainstormers (often on other machines), multiplexes their NEED questions into one pane queue for the owner, routes ANSWERs back, and delegates launch and dual-review approval to coordinators (the brainstormer

• brainstormer-dashboard-needs

  Use when running as a brainstormer or researcher whose steward/coordinator publishes NEEDs to the human via a dashboard board — author NEEDs as answerable action-picks, consume routed ANSWERS from dashboard results, and keep the board's view of your question in sync with reality.

• brainstormer-staying-current

  Use when a long-lived brainstormer worktree may be behind its configured merge target, before review or handoff, or when asked to merge-forward and leave the worktree clean. Resolves the target and merge owner from Thrum config, preserves local work, and verifies freshness after the merge.

• choosing-subagent-models

  Use before launching a subagent, an Agent or Task call, or an Explore agent, and on every review dispatch - code review, dual review, merge-gate reviewer. Picks the model and effort tier for the runtime you are running under.

• closing-findings-while-warm

  Use whenever you are about to defer a finding, fix, or cleanup instead of doing it now - proposing a follow-up bead/issue/ticket, catching a sibling defect while wrapping up, feeling something is 'out of scope', or wanting to reach DONE faster. Also use on the manager side, when reviewing a completi

• configure-roles

  Detect environment and generate customized role-based preamble templates for your Thrum agents. Creates .thrum/role_templates/ files that auto-apply on agent registration.

• conversation-only-context

  Use at the START of any long-lived agent session (researcher, coordinator, orchestrator, brainstormer), and whenever the operator says we are going to have a long conversation, get a lot done, or keep many threads open - also when context is climbing, when several investigations are in flight at onc

• coordinator-assessing-agent-completion

  Use when deciding which live agents are finished and can be stood down - 'who can I shut down', 'which agents are done', 'reap dead worktrees', 'reduce the worktree count'. Builds a candidate list checked by direct liveness, never a kill list.

• coordinator-branch-split-on-block

  Use when a merge gate (hotpath, philosophy) or dual review BLOCKS on ONE concern of a branch that bundles multiple independent concerns, while the other concern(s) are clean - on a live multi-writer shared branch. Walks the split-land-recut sequence - separate the blocked concern from the clean one(

• coordinator-dashboard-human-loop

  Use when the coordinator publishes or maintains a dashboard board FOR the human owner (roster, NEED queue, owner decisions, pipeline) or routes owner answers from a dashboard back to agents. Loads the human-loop mandate - a posted question is a PROMISE — it stays answerable and visible until answere

• coordinator-deploying-a-node

  Use when deploying a build to a single node, migrating or not — deploying a build, schema-migrating deploy, pro-bundle install plus service restart on a node, roll out a build to a node, ship to a node, single-node canary. Loads the deploy runbook — verifying the artifact actually CONTAINS the fix,

• coordinator-dispatching-work

  Use when starting an epic, dispatching to an implementer or orchestrator, choosing or re-routing which orchestrator gets a task, creating a worktree for an agent, or spawning a sub-agent. Loads coordinator-specific discipline for kicking off implementation work - routing by requirement and checking

• coordinator-hotpath-merge-gate

  Use when a hot-path merge gate is dispatched to you or you are its Gate Runner, or before a coordinator runs git merge after a clean dual review. Loads the gate-runner restart rule and the hot-path lenses from the hotpath gate config.

• coordinator-interacting-with-the-owner

  Use before writing to the human owner, escalating, or composing a thrum send or reply with prose - 'notify the owner', 'escalate', 'a notification just arrived', 'before restarting on a context reading'.

• coordinator-managing-state-and-lifecycle

  Use when ending a session, when updating project state, when managing beads epics, or before session close. Loads coordinator-specific discipline for owning project state and shepherding the team's lifecycle.

• coordinator-merging-code

  Use the moment code is presented for merge - a merge report arrives, an agent says MERGE-READY or RECOMMEND MERGE or the branch is ready, you are asked to approve or land or ship a branch, you are about to run git merge, or you are consolidating review findings before a merge. Loads the full merge s

• coordinator-philosophy-merge-gate

  Use when ABOUT TO START a philosophy merge gate - a gate has been dispatched to you, you are picking up a queued gate, you are the Gate Runner beginning a gate - and when a coordinator is about to run git merge on any new feature or large bug fix after dual review came back clean. Loads the gate-run

• coordinator-plan-reconcile-gate

  Use when parallel plans for one shared idea are all locked and about to feed project-setup, to check they compose at shared seams before any bead or worktree exists. Uses Fable, the one standing exception to the never-select-Fable rule.

• coordinator-rolling-out-to-nodes

  Use when rolling a build across all nodes — fleet deploy, rolling the nodes, deploy everywhere, ship to every node, canary then the rest, promote the canary, staged rollout, deploying after a merge batch. Orchestrates the staged order and the promotion gate between stages, and delegates each node to

• coordinator-running-autonomous-feature-development

  Use when the coordinator is idle or in a post-merge lull and a small, self-contained, reversible backlog item exists that could plausibly be developed and planned autonomously, with the finished plan still going to the human for go/no-go. Not for inventing work to stay busy, for cross-cutting / sche

• coordinator-running-brainstorm-cycles

  Use when starting a brainstorm for a bug fix, feature, or architectural decision the coordinator can't trivially decide alone — spawns a researcher in an isolated worktree, runs the brainstorm interactively with the user, iterates dual-review cycles to ready-to-merge, optionally drives an overarchin

• coordinator-running-review-cycles

  Use when an implementer reports DONE, when consolidating review findings, when handling implementer pushback on a finding, or when arriving at a review gate. Loads coordinator-specific discipline for running review cycles cleanly.

• coordinator-single-responsibility-merge-gate

  DEPRECATED — superseded by `coordinator-philosophy-merge-gate`. Invoke that skill instead. (This stub is retained for backward discoverability; it redirects immediately.)

• deviations-protocol

  Use when authoring a plan or implementation prompt - Deviations-from-Source block format, required even when empty.

• diagnosing-fleet-and-daemon

  Use when the daemon or fleet looks broken - 'daemon down', 'connection refused', 'dial unix', 'database locked', 'agent looks dead', 'where is the daemon log'. Also use before restarting any daemon, for the pre-restart migration check.

• efficient-multi-agent-research

  Use when investigating, auditing, or reviewing more than 6 items across a codebase - function call sites, pattern usage, file reviews, or any research task with partitionable items that would pollute the main agent's context if read directly

• fixing-documentation-errors

  Use the moment you notice docs are wrong, stale, or incomplete - a missing flag, a help text or llms.txt that disagrees with behaviour, a broken example. Triggers include 'the docs don't mention X', 'llms.txt is out of date', 'this example is wrong'.

• generator-idempotency-protocol

  Use when generating config or docs from templates - idempotency invariant for generator skills.

• implementer-orchestrating-execution

  Use when starting execution of a scoped implementation task — about to implement, ready to write code, executing a bd task. Loads the orchestration procedure — dispatch research, implementation, and verification to sub-agents and synthesize their output instead of doing the legwork inline.

• implementer-receiving-dispatch

  Use when receiving a new task from the coordinator, starting implementation, scoping a fresh task, or receiving dispatch. Loads implementer-specific discipline for kicking off work cleanly.

• implementer-receiving-review-feedback

  Use when receiving review findings, when a reviewer flagged an issue, during a review cycle, or when responding to review. Loads implementer-specific discipline that complements superpowers:receiving-code-review.

• implementer-status-and-handoff

  Use when reporting status to the coordinator, marking a task done, or handing off completed work. Loads implementer-specific discipline for closing the loop cleanly.

• implementer-tdd-and-quality

  Use when writing tests, running tests, hitting a quality gate, or before reporting a task done. Loads project-specific test and quality discipline that complements superpowers:test-driven-development.

• memory-maintenance

  Use when an agent needs to update, delete, supersede or audit an existing memory entry, or manage its edges, comments and hierarchy - after verification, when a finding goes stale, when a rule needs amendment, recovering a soft-deleted memory, or reading change history. Covers edit vs supersede, the

• memory-search-advanced

  Use when running thrum memory search with RAG (--near), composing complex predicate stacks, paginating large result sets, interpreting MEM-001..010 hint codes, or diagnosing embedding adapter behavior. Loads three-vector ranking semantics, length-bias caveat, and the full hint catalog.

• memory-to-thrum-pointer

  Use when MEMORY.md is near or over its read limit, or when adding a new memory entry. Moves an entry's full text into a thrum memory record and shrinks its index line to a trigger plus the thrum memory ID, with a byte-for-byte check.

• orchestrate

  Execute a plan by launching agents in tmux sessions, managing epic-by-epic execution with review gates, and preparing merge reports. Use when the orchestrator receives a plan handoff from the coordinator.

• persistent-watcher-archetype

  Use when running as a persistent watcher agent — a standing, judgment-capable Claude Code agent that watches other agents' tmux panes, auto-approves safe modals, warns on context, and escalates up a parent-reference tree. Distinct from watcher-archetype (the wake-run-exit scan/emit/report substrate)

• prime-agent

  Use on scheduled-agent wake or lean prime restart - replaces the full thrum prime briefing with a lean two-step warmup tuned for short-lived scheduled-agent invocations. Step 1 reads the inbox literally (NOT a discipline assumption); step 2 surfaces newly-shipped skills since the agent last ran.

• project-gate-setup

  Use when a project needs its landing-gate configuration established or updated - the canonical config at .thrum/gate-config.json naming the per-landing test, race and lint commands, the focused-versus-full rule, how to build the merged tree, the structural checks, the verdict log and the evidence re

• project-hotpath-gate

  Use when a project needs its hot-path gate configuration established or updated - the canonical config at .thrum/hotpath-gate.json defining trigger directories, per-concept detection patterns, and incident prose for the coordinator-hotpath-merge-gate skill. Detects every language present in the repo

• project-philosophy

  Use when a project needs its implementation philosophy established or updated — the canonical doc at .thrum/philosophy.md defining anti-patterns, red flags, and project-specific rules that implementation agents read at task-start time. First invocation generates from project inspection; subsequent i

• project-rules-protocol

  Use when loading project-specific rules - shared rule skill for role skills.

• project-setup

  Use when converting a plan file (from writing-plans skill) into beads epics, tasks, implementation prompts, and worktrees — before any coding begins

• researcher-answering-queries

  Use when another agent has asked you a research question, when fielding a research request, or when responding to a query. Loads the lookup-and-respond protocol so cached findings get reused before fresh investigation starts.

• researcher-investigating

  Use when investigating, exploring code, working on a research task, when asked to find me X, or to investigate Y. Loads researcher-specific discipline for running an investigation cleanly.

• routing-messages-across-daemons

  Use when thrum send fails with unknown recipient, when sending a cross-box message to an agent on another daemon, when there is no second hop, when you need to route or relay through a paired peer, reach an agent on another box, or tmux send to a remote agent.

• setting-up-account-usage

  Use when the user wants to see account usage, quota, usage limits, rate limits or their plan usage, when thrum team shows no Accounts section or the line Usage not enabled on daemon, when account usage says not_installed, version_mismatch or unavailable, or when setting up quota-axi for the daemon a

• snapshot-protocol

  Use when composing a restart snapshot or continuation - snapshot structure, worktree resolution, write rules.

• stamp-protocol

  Use when stamping a plan, prompt, or snapshot - Authored-against format, derivation commands, never-type rule.

• state-migration

  Use when your agent-local thrum state is empty AND you have an existing State.md file in your agent directory - this is a ONE-TIME conditional onboarding that fires only on that exact combination. Do NOT use if thrum state already has entries (nothing to migrate) or if you have no State.md (brand-ne

• steward

  Use when running as a Steward - a persistent watcher that carries questions between several projects' coordinators (and brainstormers) and the project owner, sends them to the owner's inbox, and carries the owner's answers back with project and sender context. Never decides content.

• thrum-memory

  Use when capturing, reading or querying structured memories (session summaries, architectural decisions, restart snapshots, agent rules) via the thrum memory CLI - writing a role-rule, looking up rules at session start, recalling a topic, or checking what a memory should say before you write it.

• thrum

  Multi-agent coordination via messaging, groups, and shared context. Use when agents need to communicate, delegate work, or coordinate across worktrees.

• trace-spec-to-plan

  Use before converting a plan into epics/beads/worktrees, and whenever you need to know whether a plan actually implements its spec. Walks EVERY requirement in the spec forward into the plan, one item at a time, and reports PLANNED / NAME-ONLY / ABSENT / PARTIAL. Distinct from verify-against-source,

• update-queue

  Use to reconcile your own thrum queue against ground truth - 'update my queue', 'audit my queue', 'my queue is stale', 'reconcile the queue', 'clean up done bundles', or at any session start / lull when you are about to conclude nothing is pending. Verifies each live bundle against git + beads + mer

• using-monitors

  USING thrum monitor to schedule reminders, periodic script checks and pane nudges; use when asked to set up a monitor or verify one delivered

• using-the-dashboard

  Use when you want to present an interactive board to the human user (status, options, NEEDs with A/B/C picks), or when you see a dashboard mention and wonder what is actually usable today. Carries the CLI surface, the write/read discipline, and the live-vs-coming honesty table.

• using-the-queue

  Use to track your committed work or see who is doing what - 'what is on my plate', 'promote a backlog bead', 'assign work', 'nothing pending'. Also run it before concluding you are done, to reconcile committed work against the queue.

• using-thrum-state

  Use when reading or writing thrum state - your session-start state, next actions, a fleet fact like deploy state or topology, or a stale-row freshness ping. Confirm each row is measured, not guessed, before you write it.

• using-tmux-ssh

  Use when about to ssh to a host, run a command on a VM or remote box, start a long test or build on another machine, inspect a remote log, or recover after an ssh connection dropped or a remote command timed out. Use tmux-ssh for remote commands, saved-watch resume, and concurrent observation.

• verify-against-plan

  Use after implementation is complete to verify the code covers every requirement from the plan / design spec - runs alongside code-review as the second pass in the Code Review Protocol. Takes an optional design= input so requirements that only the design doc states are checked too. Outputs structure

• verify-against-source

  Use when verifying that a prose artifact (brainstorm, design spec, plan, or implementation prompt) honors its input/source artifact(s) - the prose counterpart to verify-against-plan. Runs as the conformance axis of the planning-skill review loop. Outputs structured findings - missing scope, silent d

• watcher-archetype
• writing-durable-markdown

Slash commands (13)

• /thrum:compact

  Stage and verify a comprehensive snapshot, settle owned background tasks, then compact this tmux session in place. Use for designer or architect work needing wire contracts, a capability matrix, and design rationale.

• /thrum:inbox

  Check message inbox

• /thrum:load-context

  Restore your session after compaction or session restart by running thrum prime

• /thrum:overview

  Combines identity, team, inbox, and sync status

• /thrum:prime

  Load AI-optimized session context

• /thrum:quickstart

  Register agent and start session

• /thrum:reply

  Reply to a message

• /thrum:restart

  Save a comprehensive 16-section restart snapshot and prepare for session restart. Use for designer/architect-grade handoffs needing wire contracts, capability matrix, anticipated Q&A, and design rationale.

• /thrum:send

  Send a message to an agent

• /thrum:sleep

  Park this agent for operator-initiated wake with a comprehensive 16-section snapshot (does NOT signal coordinator) then thrum-tmux-kills own session. Use for designer/architect-grade work where wake may be cold and must recover wire contracts, capability matrix, and design rationale.

• /thrum:team

  Show active team members

• /thrum:update-project

  Update project state with session summary and mechanical state

• /thrum:wait

  Block until a message arrives

Subagents (1)

• message-listener

  Background listener for incoming Thrum messages. Runs on a cheap tier (see choosing-subagent-models) for cost efficiency. Uses `thrum wait` with PID file coordination to prevent duplicates. Returns immediately when new messages arrive. - Bash

Hooks (7)

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/block-sync-worktree-cd.sh

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/block-tls-key-exfil.sh

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}"/hooks/memory-rule-jit/hook.sh

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}"/scripts/inject-prime-context.sh

• Stop

  "${CLAUDE_PLUGIN_ROOT}"/scripts/stop-check-messages.sh

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}"/hooks/memory-pointer/hook.sh

• PostCompact

  "${CLAUDE_PLUGIN_ROOT}"/scripts/post-compact-recover.sh

Similar plugins