Top 6 OpenCode 2.0 Skills That Actually 10x Your Workflow, 100% Free & OpenSource

You are helping me turn one specific YouTube video into real, durable learning.

Source video:
- Title: Top 6 OpenCode 2.0 Skills That Actually 10x Your Workflow, 100% Free & OpenSource
- URL: https://www.youtube.com/watch?v=cP7-0dn716E
- Topic: Interfaces + Open Design
- My current learning frame: Create a six-row decision matrix for GitNexus, Matt's skills, UI UX Pro Max, Claude Mem, ECC, and Caveman, recording each pain point, mechanism, prerequisite, license or service caveat, and overlap risk before testing only the best-fit choice on a small task.
- Why this matters: New playlist item from AI Stack Engineer; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:20 / Evidence 1: "between sessions. It doesn't know how your code fits together, and it burns tokens on stuff you never asked for. So today, I'm going through six open-source repos that can 10x your open code workflow. And the last..."
- 2:27 / Evidence 2: "between two functions, and detect changes, which you run before a commit. Setup is two commands from your project root, NPX Git Nexus analyze, then NPX Git Nexus setup. The first indexes the code, installs the skills, and..."
- 4:20 / Evidence 3: "the plan is actually clear. Honestly, this one alone changes the output more than switching models. Grill with docs also builds a shared vocabulary file, now called glossary.md. Once the agent knows your project's terms, it stops using..."
- 6:22 / Evidence 4: "off-limits. Version two has 192 reasoning rules, 192 color palettes, 74 font pairings, 119 UX guidelines, and 22 tech stacks, including Laravel with Blade, Livewire, and Inertia. For open code, run npm install -g ui-ux-pro-max-cli. Then inside your..."
- 9:36 / Evidence 5: "pieces, ECC gives you an entire system with agents, skills, commands, hooks, rules, memory, and a security scanner called Agent Shield. The workflow it pushes is plan, test, implement, review, verify, remember, then improve. And the review step..."
- 11:11 / Evidence 6: "mentioned at the start. It started as a joke in April 2026. The idea was to make the agent talk like a caveman, so it uses fewer tokens. It hit number one on Hacker News, and the prime..."
- 12:57 / Evidence 7: "account, and it shows up in open code's model picker. If you only want short answers, install just the skill with npx skills add juliusbrussy/caveman-g. The CLI sends usage stats by default, so turn that off with caveman..."

Video-aware target:
- Prompt lane: Context/search
- Mechanism to extract: Extract how context is found, filtered, refreshed, and handed to the agent before it acts.
- Artifact to produce: A context retrieval map with source inventory, indexing/search path, query rules, freshness checks, and agent handoff.
- Artifact must include: source inventory; index/search layer; query rule; freshness check; agent handoff; proof behavior

Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Extract how context is found, filtered, refreshed, and handed to the agent before it acts. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A context retrieval map with source inventory, indexing/search path, query rules, freshness checks, and agent handoff.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Work question -> Source inventory -> Index/search layer -> Retrieval rule -> Agent context -> Answer/proof -> Maintenance
   - answers to these source questions: What source is searched or indexed? | What query/retrieval rule is demonstrated? | How does the agent use the retrieved context?
   - 3 concrete examples that apply the video idea to real agentic work, such as codebase memory; personal wiki retrieval; Elastic search context engineering
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: dumping all context; stale memory; retrieval with no proof trail
   - a checklist for the next real workflow, focused on: sources, query, freshness, handoff, citation/proof
   - one practical exercise with a clear done signal: Write three retrieval queries for one real project and define what each must return.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.

Quality bar:
- Make this specific to "Top 6 OpenCode 2.0 Skills That Actually 10x Your Workflow, 100% Free & OpenSource", not a generic Interfaces + Open Design essay.
- Cite the transcript wherever the prompt names a task boundary, review habit, context move, or verification standard.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic context-window advice; memory hype without retrieval rules; source claims without freshness checks.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.