All versions since 5.2.0 (2026-04-01)
5.2.0 (2026-04-01)
Features
5.2.1 (2026-04-06)
Bug Fixes
5.2.2 (2026-04-06)
Bug Fixes
5.2.3 (2026-04-06)
Bug Fixes
6.0.0 (2026-04-10)
⚠ BREAKING CHANGES
- dev: migrate workflow state from .claude/ to .catalyst/ (#63)
Features
6.0.1 (2026-04-13)
Bug Fixes
- dev: add fully-qualified plugin prefixes to skill references (#69) (f9e69f2)
- dev: initialize workflow context and OTEL ticket early (#73) (3406c30)
6.0.2 (2026-04-13)
Bug Fixes
6.0.3 (2026-04-13)
Bug Fixes
6.1.0
Apr 25, 2026
AI-Native Estimation Signal Schema
Foundation data contract for ticket estimation across all PM plugins. Every estimation skill now reads and writes the same estimation: YAML block with standardized fields for scope, confidence, methodology, and uncertainty modeling. Linear primitives (Issue.estimate, labels) mirror the schema for native filtering and burndown while YAML frontmatter remains the source of truth.
PRs
[7.0.0] — 2026-05-11
⚠ BREAKING CHANGES
catalyst-pm is now a focused strategy and definition plugin with 12 skills. 30 skills have moved to companion plugins:
- 12 skills → catalyst-pm-ops:
analyze-cycle,analyze-milestone,groom-backlog,create-tickets,sync-prs,daily-plan,weekly-plan,weekly-review,report-daily,status-update,slack-message,connect-mcps - 4 skills → catalyst-meeting-hygiene:
meeting-agenda,meeting-notes,meeting-cleanup,meeting-feedback - 14 skills → catalyst-discovery:
user-interview,user-research-synthesis,interview-guide,journey-map,competitor-analysis,retention-analysis,activation-analysis,feature-metrics,experiment-metrics,experiment-decision,metrics-framework,prototype,prototype-feedback,napkin-sketch
The following skills are permanently removed (not moved):
generate-ai-prototype— subsumed byprototypein catalyst-discoveryinterview-prep— PM job-search tool, out of scope for project pluginsinterview-feedback— PM job-search tool, out of scope for project pluginscontext-daily— incomplete; dependencies (github-metrics,thoughts-metrics,context-analyzer) do not exist
7 support agents removed (only linear-research remains): context-analyzer, github-metrics, thoughts-metrics, calendar-analyzer, health-scorer, code-classifier, linear-metrics.
Skills retained in catalyst-pm (12): prd-draft, prd-review-panel, ralph-wiggum, define-north-star, impact-sizing, prioritize, write-prod-strategy, expansion-strategy, strategy-sprint, decision-doc, launch-checklist, feature-results
Upgrade path
Install the companion plugins to restore moved skills:
/plugin install catalyst-pm-ops/plugin install catalyst-meeting-hygiene/plugin install catalyst-discovery7.0.0
May 11, 2026
Plugin Restructure & Meeting Hygiene
The bloated catalyst-pm plugin splits into four focused tools: catalyst-pm (12 strategy/PRD skills), catalyst-pm-ops (Linear integration and cadence), catalyst-meeting-hygiene (agenda through feedback workflows), and catalyst-discovery (research and prototyping). Skills moved to new plugin paths like /catalyst-pm-ops:daily-plan and /catalyst-meeting-hygiene:meeting-notes, so update any hardcoded references in your workflows.
PRs
- pm: shrink catalyst-pm to 12 strategy/PRD skills (CTL-322) (#543)
- pm: extract meeting workflow skills into catalyst-meeting-hygiene plugin (CTL-320) (#541)
- pm-ops: extract Linear/cadence/comms skills from catalyst-pm (CTL-319) (#537)
- pm-ops: extract Linear/cadence/comms skills from catalyst-pm (CTL-319) (#537) (5a9c582)
- pm: extract meeting workflow skills into catalyst-meeting-hygiene plugin (CTL-320) (#541) (ba0c12a)
- pm: shrink catalyst-pm to 12 strategy/PRD skills (CTL-322) (#543) (43b1c89)
7.1.0 (2026-06-03)
Features
- pm: AI-native estimation tooling — corpus extractor, calibrated scorer, reference-class lookup (CTL-746) (#1265) (4f56000)
7.2.0 (2026-06-08)
Features
- pm: close the estimation feedback loop — recurring corpus refresh from real actuals (CTL-813) (#1400) (f066c82)
7.3.0
Jun 30, 2026
Evidence-Based Linear Read Path
Agents now follow a single canonical rule for reading Linear: on standard nodes they call linearis directly, and on Catalyst Cloud nodes they read the replica first and only escalate to a direct read if there’s concrete evidence of staleness. This eliminates the scattered, conflicting guidance that was pointing agents at the retired read mirror. No migration needed — the daemon already handles mode resolution automatically.
PRs
- dev: CTL-1392 — agents read the Catalyst Cloud replica first (evidence-based fallback) (#2474) (5599fe9)
7.4.0
Jul 01, 2026
Enforced Linear Read Path
The linearis skill now mandates that all agent and script Linear reads go through catalyst-linear read|list|search instead of calling linearis directly. This prevents bare reads from bypassing the local replica and burning shared API quota on rate-limited workers. Scripted read swaps for the .sh helpers and phase skills land in a follow-up PR.
PRs
- dev: CTL-1397 (1/n) — mandate Linear reads via catalyst-linear (linearis skill + research agents) (#2496) (27ab1fe)
7.5.0
Jul 02, 2026
Direct SQLite Linear Reads
Agents now query the local Catalyst Cloud replica (~/catalyst/catalyst-replica.db) directly with SQL instead of routing through the catalyst-linear CLI wrapper, giving them full access to issues, labels, and relations in a single query — including joins the CLI couldn’t do. A freshness gate mirrors the daemon’s own liveness checks, and any stale or missing replica triggers a loud fallback to linearis rather than a silent reroute. The catalyst-linear CLI is now deprecated and kept only as a compatibility shim.
PRs
- dev: CTL-1397 — pivot agent Linear reads to direct SQLite; deprecate catalyst-linear CLI (#2514) (249c9d6)
7.6.0 (2026-08-04) Latest
Features
- dev: CTL-1628 catalyst-runtime-root resolver — fold Tier 1 duplicates + 4 latent resolver bugs (Phase A2) (#2946) (c01ef76)