System updates. The work changed, dated and linked.
Read changes to the licensed systems and their original standalone editions. Versions follow publication dates; historical prices describe the edition at that time.
Review compatibility in your purchased repository, preserve local configuration, then repeat one representative task before expanding use. A published note alone does not prove that a workspace has been updated.
Latest published system releases are shown below. URL filters and page selection need JavaScript in this view. Read published updates in RSS.
Matching published releases
24Across the selected system history and change type
Releases on this page
12Page 1 · up to 12 records
Systems represented here
3This page only; includes archived standalone offers
Clearer operating safeguards connect account economics, campaign controls and reporting, while preserving your buyer setup and included installation support.
Inspect the published highlights
Campaign economics first - check account currency, shared budget owners and protected campaign roles before pooling or expanding spend.Consistent operating controls - shared guidance connects feed, bidding, platform settings and destination checks across the existing workflows.Evidence-aware reporting - retain reporting ownership and creative evidence without treating a prepared report as permission to deliver it.134 skills retained - the skill roster stays intact, including the five workflows introduced in version 1.6.0.Setup and support preserved - keep your non-overwriting setup helper, privacy rules, adoption guide and included installation and initial process-integration support.
Five new workflows connect prospect audits, persona research and creative variations. Buyer setup is preserved and report handoffs carry clearer evidence.
Inspect the published highlights
Five new workflows - add prospect audits, a shared persona center, speaker-congruence review, situation selection and static-ad variations.Complete buyer inventory - 134 skills, eight project subagents, 1,184 Python utilities and 149 shared Python libraries, measured from the release candidate.Buyer setup preserved - keep the non-overwriting initializer, its regression test, privacy rules and adoption guide when updating.Reporting handoffs - carry fuller monthly reporting evidence and consistent published-source hashes into configured delivery workflows.Creative references stay yours - use the written style catalogs and your own approved images; vendor example-image archives are excluded.Safer adoption instructions - separate local setup, provider access, a reviewed first result and any live launch approval.
A maintenance release that makes setup safe to repeat and ships the commercial license. Package metadata now reports the release version. Workflows, skills and access are unchanged, and /update takes it with no re-clone.
Inspect the published highlights
Setup keeps your keys - the README, QUICKSTART and UPGRADING setup steps no longer overwrite an existing .env when you run them again.Package version fixed - pyproject.toml reports the release version; in 2.0.0 it still said 1.1.1.Commercial license ships - LICENSE is in the repository and the README license line points to it and to the Tegra terms.Nothing else changes - 78 working skills, 6 slash commands, 34 specialist agents and 17 enforcement hooks, exactly as in 2.0.0.
The End-to-End Codebase is reorganized into 129 broader skills, down from 178, with 72 narrower skills now running as modes of one canonical skill each. New in this release - a five-skill Funnelish lane, nine new creative-generation packs, eight specialist subagents, and a larger engine with 1,142 Python utilities, up from 987. The bundled Higgsfield skills no longer ship. This release also ships as a fresh repository history, so re-clone your copy instead of pulling.
Inspect the published highlights
Reorganized roster, 178 to 129 skills - 72 narrower skills now run as a mode, surface, channel or medium of one canonical skill, so each job has one name. Every retired name maps to its replacement.Funnelish lane (5 new skills) - audit published funnels without a login, build and edit funnels one approved change set at a time, onboard a brand, run A/B and geo tests, and install the tracking standard.Nine new creative packs - aggressive statics and long-form primary text, native story ads, ad clones, micro-drama, two-host podcast, sung, talking-head and general video ad writers.Eight specialist subagents - focused reviewers for ad copy, buyer personas, comprehension, image ads, spend safety, page review, performance analysis and repo search.Consolidated workflows - client reports, tracking installs, campaign expansion, feed copy tuning, Demand Gen uploads, page improvement, roasts and SEO content each run from one skill now.A larger engine - 1,142 Python utilities, up from 987, and 136 core libraries, up from 70, plus project hooks that run automatically from the settings file.Retired: the Higgsfield studio skills - the eight bundled Higgsfield skills no longer ship. Copies you already have keep working.Fresh repository history - this release ships as one clean commit, so a plain pull will fail. Re-clone your repo, or fetch and reset, as described below.
This release rebuilds the system around 78 Claude Code skills. Rendering now ships end to end, daily media buying runs as one approved pass, competitor research is rebuilt, and the repository restarts from one clean commit, so re-clone it once.
Inspect the published highlights
Skill-first harness - 78 Claude Code skills replace the old command surface, with 34 specialist agents and 17 enforcement hooks. Research stages run inline in your session.Rendering ships end to end - static rendering, voiceover, animation on Kling, Seedance, Wan and Grok lanes, assembly, captions, text cards, colour grade, sound and glue all run inside the product.Daily media buying in one approved pass - fb-daily runs clean, budget step, bid step and graduation, then asks one approval question before anything is written to Meta.New static and video lanes - angle, fire and landing-page static lanes, static variations of your winners, static-to-video, static-to-doodle and talking-head yapper videos.Competitor research rebuilt - spy-search, spy-pick and spy-pages find, keep and decode competitor ads and pages, and static-clone turns a strong look into your own creative.Safer updates and a clean repository - update merges each release into your copy and never rebases. The repository history restarts from one clean commit, so re-clone it once.
The September release added a guarded Meta lane, asset census, creative production tools, product-collection offers and Taboola audience preparation.
Inspect the published highlights
Native Meta Ads launch lane (4 new skills) - meta-prep, meta-launch, meta-report, and meta-autogrow. Build a research-grounded campaign package, launch it paused behind a two-step human approval, read canonical performance, and run a weekly kill, refresh, and scale cycle. Meta now has the same guarded-launch discipline as Google.Cross-platform asset census (1 new skill) - brand-asset-census reads every live Google Ads asset and every Taboola item, judges each one in context with a spend floor and Poisson significance, and writes one Google Sheet per brand with a swap plan. Read-only, so it is safe to run any time.Higgsfield creative studio (8 new skills) - generate images, video, 3D, and audio, plus brand kits, product photoshoots, marketplace cards, explainer videos, YouTube thumbnails, consistent characters, and full websites. Ships with its bundled helper scripts.Pollection offer pages (1 new skill) - offer-pollection builds a Shopify page with a feed-approved buy box on top and a filterable category grid beneath it, the right destination for generic category searches where the buyer is still choosing between products.Taboola first-party audiences (1 new skill) - taboola-audience-sync onboards your buyer ledger as Taboola audiences and runs lookalike discovery, dry-run by default.Leaner roster - eight alias skills and two unused router skills were retired. Every capability they pointed at is still here under its canonical name.The complete engine now ships, not just what each skill points at - the full utility layer (987 Python utilities, up from 682), every core library, schema, data contract, page block, and seed data file is included, along with the scripts and templates that live inside skill folders. Nothing a skill calls is missing from your copy.
This August 20 release added the story production lane and fixed executable modes for the shipped hooks and scripts.
Inspect the published highlights
The story lane (7 new skills) - advertorial-write and advertorial-deploy take a 2,000-4,000 word destination advertorial from section-by-section authoring to a live styled page registered as a typed offer surface; story-avatars-and-angles converts your house personas and typed angles into the lane's avatar contract; story-ads and story-native-ads generate avatar-driven static and native creatives; story-copy and story-video produce closed-pack story feed copy and spine-first story video.A second complete process, not a variant - the story lane runs beside the house lanes (generate-static, native-feed, spielberg, tarantino) on the same personas and angle registry, so you can produce and test both processes against each other on one offer.Hooks and scripts now ship executable - earlier packaging stripped file modes; all 22 enforcement hooks and every script now carry the executable bit out of the box.Cleanup - test files for the decommissioned Layer-3 orchestrator and the non-shipped research corpus were removed; autonomy is the nightly scheduler plus /scale-plan and /director.
The August 19 release replaced overlapping angle commands, added native-feed and another video-authoring lane, and strengthened the shipped rules and hooks.
Inspect the published highlights
The angle engine, consolidated - /angle-generate is now THE engine (dedup, Methods A-E, Simplicity Hierarchy, Evidence Gate, Big-Idea-strength gate) with /angle-craft for mechanism-first matrices and a spawnable angle-generator worker. The generate-angles v2-v4 lineage is retired.New creative lanes - a dedicated native-feed static family, the /generate-static v3 pipeline, Tarantino video authoring next to /spielberg, video-song, and creative element mining.Rules layer 11 → 23 files - advertorial compliance, brand style, funnel-ad contract, gate-enforcement map, hook boards, image/video buyer rules, Meta naming, policy registry, and testing structure now ship as explicit rules.Knowledge graph 423 → 466 canon nodes - plus a refreshed atom-graph tooling layer and expanded visual-craft + narrative libraries.Agents consolidated 108 → 38 - the metadata audit merged overlapping single-purpose workers into stronger consolidated specialists; every capability is preserved. Skills grow 81 → 97.Hardened enforcement - 4 new hooks (git hygiene, dirty-tree monitoring, session state sweeps) bring the guard count to 22.
This August release added a seven-skill native-ad pipeline, adversarial creative review, AI Max workflows and advertorial presells.
Inspect the published highlights
Taboola is now a first-class deploy surface (7 new skills) - prep, mine, launch, expand, harden, autogrow, and report. Includes publisher screening with tiered auto-blocking, day-1 realtime launch watch, and a pre-spend reach estimator. Together with the existing Google Ads engine and Microsoft Ads lane, the system now runs three deploy surfaces from one folder.Adversarial roast panel (4 new skills) - roast-copy, roast-image-ad, roast-video-ad, and roast-presell put every asset in front of a hostile expert panel before money touches it.AI Max search (2 new skills) - launch and autogrow Google's AI Max search campaigns alongside your classic Search builds.Advertorial presell pipeline (2 new skills) - write and deploy editorial advertorial presells end to end, the highest-performing page class in the theme library.Deeper feed + cross-channel engine - brand shopping feeds, category testing, feed sharpening, PMax consolidation, Meta-to-Google creative push, competitor spy briefs, audience sync, angle-performance mining, and campaign-level optimization.Two editions, one upgrade for existing owners - the product now ships as Blueprint ($4,997) and End-to-End Codebase ($19,997). Every Agent Codebase owner has been upgraded to the full End-to-End system at no charge - pull the latest from your private repo.
This July release introduced research, angles, static/video production and guarded launch preparation for Meta operators.
Inspect the published highlights
New flagship - The complete AI creative agency for Meta ads - research, angles, statics, AI video, spy, guarded launches52 commands / 81 skills / 108 agents - The full production harness plus a 989-file Python control plane423-node knowledge graph - Distilled ad-craft memory the creative pipelines load at runtimeTwo tiers - Blueprint $4,997 / Full Agentic System $19,997 (private GitHub repo, lifetime updates)
This June release expanded the Google codebase into page, creative and Demand Gen preparation and migrated workflows to Claude Code Skills.
Inspect the published highlights
Agent Codebase supercharged: 40 → 89 skills - it's now a complete Google Ads growth system that builds your landing and offer pages end-to-end, generates your image and video creative, runs your demand-gen campaigns, and drives your Search, Shopping, and PMax engine, all from one folder.The whole system is now Claude Code Skills - every capability is a self-contained .claude/skills/<name>/ folder with a lean SKILL.md and references that load only when a task needs them. Faster, cleaner, easier to extend - and nothing was removed.Two brand-new domains in the End-to-End Codebase - Meta Ads (7 skills) to repurpose your Google creative into Meta paid social, and SEO (4 skills) to turn paid-search demand into organic ranking. The End-to-End surface is now 149 skills.Your framework reference library now ships with the code - design standards, hook taxonomy, VSL/video structures, quality-gate specs and more are bundled in, so every skill is genuinely self-contained.Pricing unchanged - the Agent Codebase stays at its current price and is now a dramatically stronger value.
This June release migrated the optional codebase to 45 Claude Code skills and added the Demand Gen growth loop, while the curriculum remained unchanged.
Inspect the published highlights
45 skills, one creative-to-campaign workflow - The Agent Codebase moved from slash commands to 45 Claude Code skills spanning brand analysis, creative briefs, image/video generation, expert review, and the full Demand Gen pipeline.The Demand Gen growth loop - New demandgen-autogrow and demandgen-expand skills run a weekly diagnose → promote winners → retire losers → expand loop, every change in dry-run until you approve it.49 image + 22 video creative themes - The theme library grew to 49 image and 22 video themes, auto-matched to your brand so new creative inherits proven visual grammar instead of starting from scratch.Meta → Demand Gen repurposing - New meta-image-repurpose and meta-shorts-repurpose skills turn your best Meta creative into Demand Gen-ready assets.Competitor creative-trend spy - The spy-meta-trend and spy-replicate skills surface which creative territory is crowded and which is open, then help you move first.Quality gate on every asset - creative-review and creative-refresh-review score each asset against the 13-Point Creative standard before it spends a dollar.
System updates. The work changed, dated and linked.
Read changes to the licensed systems and their original standalone editions. Versions follow publication dates; historical prices describe the edition at that time.
Review compatibility in your purchased repository, preserve local configuration, then repeat one representative task before expanding use. A published note alone does not prove that a workspace has been updated.
Matching published releases
24Across the selected system history and change type
Releases on this page
12Page 2 · up to 12 records
Systems represented here
3This page only; includes archived standalone offers
This June release moved the landing-page codebase to 51 skills and included 92 presell plus 17 offer theme packages, while leaving curriculum counts unchanged.
Inspect the published highlights
Agent Codebase migrated from slash commands to Claude Code Agent Skills - the codebase now ships 51 skills (was 45 commands)Page theme library now ships - 92 presell + 17 offer themes (109 packages) included in the Agent Codebase4 new skills - presell-quiz-autogrow, presell-kill, offer-smoke-test, brand-voice-calibrate
This May 20 release expanded Meta/Demand Gen connections, readiness gates and resumable pipeline orchestration around the landing-page workflow.
Inspect the published highlights
Meta integration - 6 new commands: onboard, creatives, performance, image + shorts repurpose, PMax-launchPaid-launch safety - Pre-flight readiness + quality gates before any presell or offer hits paid trafficFull Demand Gen pipeline - End-to-end image + video Demand Gen authoring and uploadPipeline orchestration - New /run picks the right pipeline for your stage; /workflow runs multi-stage with checkpoints
The May 20 release added Meta research/repurposing commands, prelaunch checks, resumable workflow runners and stronger competitor evidence.
Inspect the published highlights
Meta integration - 6 new commands: onboard, creatives, performance, image + shorts repurpose, PMax-launchPaid-launch safety - /presell-paid-launch-readiness + /offer-paid-launch-gate catch broken URLs and tracking gaps before you spendPipeline orchestration - New /run + /workflow top-level runners with checkpoints and resumeSharper competitive intelligence - Cleaner signal extraction across /spy-demand-gaps, /spy-demand-brief, /spy-search-ad
This May 17 curriculum release integrated standalone deliverables into chapters and added 14 new practical assets.
Inspect the published highlights
14 new deliverables - Hands-on assets across the program, designed to shipCurriculum reorganized - 14 standalone deliverables folded directly into chapters~15% content refreshed - Sharper explanations, tighter examples, less context switching
The May 17 release added the production operator module and PostHog experiments-backfill material while relocating deliverables into the curriculum.
Inspect the published highlights
Module 17 added - Production-Grade Presell + Offer Operator System (April 2026)PostHog Bayesian Experiments Backfill - New chapter 4 inside Module 17 for cohesive operator workflow18 new deliverables - Ready-to-ship presell + offer assets across the curriculumFeatures list refreshed - Now reflects what's actually in the system today
The May 17 release reorganized the introduction and tier map, revised Modules 22/23, and placed deliverables beside the work they support.
Inspect the published highlights
Module 22: run-demandgen Workflow Router - Revised Conclusion ties the workflow together more cohesivelyModule 23: Full Creative System - Clearer rules for what's reserved for the AI Agentic System tierTier Map + Introduction restructured - Sharper onboarding and tier picture11 new deliverables + features refreshed - Plus standalone materials folded into the right chapters