FreeBuff: 100% Free & Unlimited Coding Agent, No Subscription, No API Key

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

Source video:
- Title: FreeBuff: 100% Free & Unlimited Coding Agent, No Subscription, No API Key
- URL: https://www.youtube.com/watch?v=SsUsGFHfXrk
- Topic: Codex + Claude Workflows
- My current learning frame: Install FreeBuff in a throwaway project and run the reviewer's first-test prompt ('What is the purpose of this project and which tech stack is it built on?') to judge whether the agent actually reads your files before you trust it with edits.
- 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:
- 0:00 / Evidence 1: "There are so many coding agents these days. You've got Claude Code, Codex, Open Code, Anti-Gravity, Klein, and a bunch more showing up every few weeks. They're good tools, but almost all of them ask for money somewhere."
- 2:16 / Evidence 2: "run commands, and work through the task with you. Instead of dumping a wall of text you have to paste somewhere yourself. Compare that to the others for a second. With Claude Code, you're tied to Anthropic's models..."
- 4:32 / Evidence 3: "dark theme toggle. The readme lists nine specialized sub-agents in total, covering things like file picking, code review, and deep thinking. Models are where it gets more interesting and where you need to slow down a little. For..."
- 7:36 / Evidence 4: "workspace, which some people will dislike on principle. The biggest honest limitation, though, is the models. There are no frontier models here. You're not getting Claude Opus. You're not getting GPT-5 level reasoning. You're not getting Gemini Pro."

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, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A routing matrix for when to use Codex, Claude, browser checks, or manual review.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Inspect -> Plan -> Edit -> Verify -> Review -> Route
   - 3 concrete examples that apply the video idea to real agentic work
   - 2 failure modes the video helps prevent
   - a checklist I can use the next time I run Codex or Claude
   - one practical exercise with a clear done signal
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 "FreeBuff: 100% Free & Unlimited Coding Agent, No Subscription, No API Key", not a generic Codex + Claude Workflows essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.