catalyst

Plugin catalyst from marketplace catalyst in TransmuteLabs/Catalyst. Commands read from the repo's manifest — 1 month ago.

Skills (15)

• arcane-mode

  Use when executing a spec or multi-task implementation plan through subagents, when writing such a plan, when verifying a completed branch against its original goal, or when a user-ordered AMENDMENT to an approved spec must be routed (any time, including mid-execution or after acceptance). Triggers

• bootup

  Use at the start of work on a new or unfamiliar project - assess agent-readiness, fill tooling gaps, and route to the right Catalyst skill. Triggers - "let's start the project", fresh clone, no build/test/lint commands known.

• campaign

  Use for a program of work spanning many sessions and multiple arcane-mode runs - several phases toward a milestone, "what's next" when a campaign exists under .catalyst/campaign/, or closing out a milestone. Not for a single feature (crucible → arcane-mode), a single foggy decision map (starchart),

• crucible

  Use when a feature idea, architectural decision, or spec needs hardening before planning - requirements are fuzzy, trade-offs unresolved, or the user wants their thinking stress-tested. Also use before catalyst:arcane-mode when no approved spec exists, and when changing or amending an ALREADY-APPROV

• debug

  Use when facing a bug, test failure, performance regression, or unexpected behavior whose cause is not yet proven - before proposing or applying any fix. Also when a previous fix didn't hold, or debugging spans context resets. Triggers - "why is this failing", "it broke", "it's slow", flaky behavior

• envoy

  Use only inside the catalyst:envoy-runner subagent and the envoy slash-commands (catalyst:envoy-review, catalyst:envoy-rescue and the rest) - the helper contract for calling the envoy companion runtime (vendor-neutral job/state/background layer; registered vendors: codex (default), grok, kimi). Resu

• forge-skill

  Use when creating a new skill or agent definition, editing an existing one, or verifying that a skill actually changes behavior - for this family or project-local skills. Triggers - "add a skill", "the skill isn't working", "update the skill", packaging session/spike findings as a skill.

• handoff

  Use when ending a session with unfinished work, before context compaction, or when resuming from a previous session's handoff document. Triggers - session wrap-up, context near limit, "continue from last time".

• install

  Use when setting up or repairing the Catalyst/ContinuousClaude toolchain - a fresh machine, missing binaries, binary-dependent features degrading, or "install/update the toolchain". Also the doctor - run it to diagnose which tools actually respond.

• premortem

  Use when a plan or spec is ready and implementation has not started - failure-state projection before work begins. The gate between an approved plan and dispatching Task 1. Also gate RE-RUNS on amended or rejected ground, and REVERSALS of a previously accepted risk (the user withdraws an acceptance)

• research

  Use for open-ended investigation where the answer is not yet known - exploring a domain, comparing approaches, understanding an unfamiliar system. Not for executing toward a known goal.

• review

  Use for standalone code review outside the arcane-mode pipeline - "review this code", "review my PR", "check before merge", "what did I break" - and for cleanup requests like "clean this up / remove the AI slop" (the deslop pass). For task review inside the pipeline use arcane-mode's critic flow ins

• starchart

  Use when an effort is too large for one agent session and the route is still foggy - you can feel the shape of the work but cannot yet write it down as a spec or a plan. Also for re-entering a standing decision map - a committed .catalyst/map/ directory in the repo. Not for well-scoped features.

• upgrade-harness

  Use when extending the ouros sandbox with a new external function - "add X search to the sandbox", "database query function from sandbox", "extend sandbox with X". Requires the ContinuousClaude binary layer (tools/ouros_harness.py present in the project).

• using-catalyst

  Use when starting a session or deciding which Catalyst skill a task needs - the family's process-skill routing and its coordination with other libraries. Injected at session start.

Slash commands (8)

• /catalyst:envoy-adversarial-review

  Run a Codex review that challenges the implementation approach and design choices

• /catalyst:envoy-cancel

  Cancel an active background Codex job in this repository

• /catalyst:envoy-rescue

  Delegate investigation, an explicit fix request, or follow-up rescue work to the Codex rescue subagent

• /catalyst:envoy-result

  Show the stored final output for a finished Codex job in this repository

• /catalyst:envoy-review

  Run a Codex code review against local git state

• /catalyst:envoy-setup

  Check whether the local Codex CLI is ready (plus grok/kimi vendor availability) and optionally toggle the stop-time review gate; a successful run is recorded per workspace and unlocks task/review/transfer

• /catalyst:envoy-status

  Show active and recent Codex jobs for this repository, including review-gate status

• /catalyst:envoy-transfer

  Transfer the current Claude Code session into a resumable Codex thread

Subagents (6)

• auditor

  Fresh-eyes audit of a branch's or milestone's final state through an assigned lens set - undirected defect search, claim-truth, goal-backward. Clean context, findings of any severity.

• critic

  Reviews one arcane-mode pipeline task - spec compliance and code quality as two verdicts, adjudication requests as a separate list. Directed verification against the brief, report, and review package.

• envoy-runner

  Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Codex through the shared runtime

• implementer

  Executes ONE task from a complete brief - implementation, tests, atomic commits, honest report. Serves arcane-mode pipeline tasks AND explicitly-marked non-pipeline dispatches (e.g. bootup's readiness run) under the same contract. Does not analyze and does not make decisions.

• researcher

  External research executor - web, docs, package analysis, repo study. Brings knowledge from outside the codebase with sources, confidence, and counterarguments. Dispatched by catalyst:research.

• scout

  Fact reconnaissance - find/list/measure/quote/cross-check with file:line. No conclusions, evaluations, or recommendations; the orchestrator chooses.

Hooks (4)

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" session-start

• UserPromptSubmit

  "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" pipeline-breadcrumb

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" dispatch-gate

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" dispatch-stats

Similar plugins