Agentic Software Factory · 2026-07-17

Oracle: Maximum Intelligence and Video

Drive ChatGPT's strongest model and Gemini's video eyes with a real browser and your own cookies — no API keys, one command after you log in.

TL;DR

🤖 Have your agent set this up — paste this into it:

Fetch https://shiny-rosette-m6zy.here.now/agent.md?raw and follow it to set this up in my current project. Run the success check at the end and show me the result.

Quick start

Sign into chatgpt.com in your normal Chrome first — a human does that part, once. Then:

npm install -g @steipete/oracle    # or: brew install steipete/tap/oracle (Node 22+)
oracle --engine browser -p "HI"    # first handshake: copies your cookies, sends "HI"
oracle status --hours 72           # the reply is recorded as a replayable session

Prompt library

The maximum-batch consult

oracle CLI → ChatGPT (GPT-5.6 Pro) your project root ordered work packages with file/function/test targets, 20–60 min later

This is the pattern behind ~1,978 real consult sessions. Fill the <angle-bracket> slots with your project's facts; the last two paragraphs ship verbatim with every consult. Save it as consult-prompt.md.

[<three-to-five-word-slug>]

## Project briefing
<stack, framework, runtime, and repo rules — two or three sentences>

## Goal
<the full outcome you want, stated as the whole contract Oracle must plan
against — never pre-shrunk to a first step>

## Prior-State Ledger
- prior_oracle_session: none
- implemented_since_prior_oracle: none
- verified_since_prior_oracle: none
- failed_proof_or_blocker: none
- remaining_goal_coverage: the full goal above

## Current evidence
<attempts, failing logs, screenshots, and known constraints — or "none yet">

## Bundle map
The attached files contain <what you included and why>. Possibly missing:
<what you could not include>.

## Deliverable
Return the maximum actionable batch: an ordered set of work packages covering
everything worth doing toward the goal. Every work package must carry exact
file/function/test targets, critical code snippets, and a falsifiable
verification. Sequence the packages, name risks and invariants, and put
anything you cannot target exactly in a separate short "needs investigation"
list.

Return your answer as text in this response only. Do not create, attach, export,
or offer any downloadable file. Do not create local project artifacts yourself.
The local agent will write any needed files, plans, notes, goals, commits, or
verification logs using local tools.

Plan the maximum actionable batch: cover everything worth doing toward the
goal in ordered work packages with exact file/function/test targets and a
falsifiable verification each. Do not return a single next step or hold work
back for a later round. An ambitious, specific answer is correct; only
untargeted vagueness is a defect.

Run it with your code attached:

oracle --engine browser -p "$(cat consult-prompt.md)" \
  --file "src/**/*.ts,docs/**/*.md" --slug "<three-to-five-word-slug>"

The sentinel video probe

oracle CLI → Gemini anywhere, with a short MP4 on disk three bullets plus the exact sentinel line, byte-for-byte

Before any expensive video run, prove the upload path with a cheap probe. Save this as probe-prompt.md:

[video-upload-smoke-probe]

This is an attached-video readiness probe for a longer video analysis run.

Confirm that you can inspect the attached video. Return exactly three short bullets:
- whether video frames are visible;
- whether audio is detectable;
- one strictly observed visual detail, without guessing.

End with this exact sentinel on its own line:
END_OF_VIDEO_ANALYSIS video-upload-smoke-probe probe
oracle --engine browser --model gemini-3-pro --browser-attachments always \
  -p "$(cat probe-prompt.md)" --file "/absolute/path/to/probe-clip.mp4" \
  --slug "video-upload-smoke-probe"

The pass rule: the sentinel comes back byte-exact and the observed detail matches your footage. A paraphrase, extra prose, or silence means the path is broken — fix it before the long run, not after.

The shard analysis prompt — Loop Craft, verbatim

oracle CLI → Gemini a video run folder with a ≤4-minute shard dense Markdown + machine JSON, ending in the exact sentinel

This exact prompt produced shard 001 of the Loop Craft wiki. Swap the metadata block and the sentinel for your own run; keep the evidence rules — they are what stop Gemini from inventing URLs, commands, and speakers.

[loopcraft-workshop-shard-001-source-native]

Analyze the attached source-native video shard for an extensive public workshop wiki.

Metadata:
- run_key: loopcraft-agent-workshop
- shard_id: 001
- original recording range: 00:00:00–00:04:00
- publication chapter: Workshop Setup and the Looping Resolver

Evidence rules:
1. Use original workshop timestamps from 00:00:00 through 00:04:00.
2. Separate spoken evidence, visible screen evidence, and inference.
3. Listen to the audio; do not rely on automatic captions.
4. Do not invent commands, URLs, files, tools, speakers, or UI labels.
5. Pull quotes must be brief (under 20 words), audio-verified, attributed to Joel Hooks, and timestamped.
6. Exclude credentials, account details, local paths/usernames, private URLs, signed URLs, notifications, or incidental personal data.
7. Treat opinions and live-demo observations as such, not universal facts.
8. Derived prompts must use placeholders, be clearly labeled as inspired by the workshop, and require confirmation for destructive or externally visible actions.

Return dense Markdown with these sections:
# Shard 001 — 00:00:00–00:04:00
## Executive Takeaway
## Dense Timeline
## Concepts and Mental Models
## Visible Demo Evidence
## Architecture and Workflow Patterns
## Tools, Commands, and References
## Pull Quote Candidates
## Copy/Paste AI Prompt Candidates
## Student Exercises and Reflection Questions
## Keyframes to Capture
## Uncertainties and Publication Review
## Machine JSON

The fenced JSON object must contain: shard_id, original_range, summary, timeline, concepts, workflows, demos, resources, quotes, prompts, exercises, keyframes, warnings, unanswered_questions.

End with this exact sentinel on its own line:
END_OF_VIDEO_ANALYSIS loopcraft-agent-workshop shard-001

Set it up (agent guide)

These steps mirror agent.md — the machine copy your agent fetches.

  1. Check prerequisites: Node 22+ and Google Chrome installed.
    node --version   # need v22 or newer; Chrome must also be installed
  2. Install the Oracle CLI.
    npm install -g @steipete/oracle
    oracle --version
  3. Sign into chatgpt.com in your normal Chrome. A human does this step — an agent cannot log in for you. Oracle borrows the session cookies from that logged-in profile.
  4. Run the first handshake. Oracle copies your cookies into a temporary automation profile, opens ChatGPT, and sends the prompt.
    oracle --engine browser -p "HI"
  5. Create your first real consult. Save this file and replace every <angle-bracket> slot with facts from your project:
    [<three-to-five-word-slug>]
    
    ## Project briefing
    <stack, framework, runtime, and repo rules — two or three sentences>
    
    ## Goal
    <the full outcome you want, stated as the whole contract Oracle must plan
    against — never pre-shrunk to a first step>
    
    ## Prior-State Ledger
    - prior_oracle_session: none
    - implemented_since_prior_oracle: none
    - verified_since_prior_oracle: none
    - failed_proof_or_blocker: none
    - remaining_goal_coverage: the full goal above
    
    ## Current evidence
    <attempts, failing logs, screenshots, and known constraints — or "none yet">
    
    ## Bundle map
    The attached files contain <what you included and why>. Possibly missing:
    <what you could not include>.
    
    ## Deliverable
    Return the maximum actionable batch: an ordered set of work packages covering
    everything worth doing toward the goal. Every work package must carry exact
    file/function/test targets, critical code snippets, and a falsifiable
    verification. Sequence the packages, name risks and invariants, and put
    anything you cannot target exactly in a separate short "needs investigation"
    list.
    
    Return your answer as text in this response only. Do not create, attach, export,
    or offer any downloadable file. Do not create local project artifacts yourself.
    The local agent will write any needed files, plans, notes, goals, commits, or
    verification logs using local tools.
    
    Plan the maximum actionable batch: cover everything worth doing toward the
    goal in ordered work packages with exact file/function/test targets and a
    falsifiable verification each. Do not return a single next step or hold work
    back for a later round. An ambitious, specific answer is correct; only
    untargeted vagueness is a defect.
  6. Run the consult with your code attached. A GPT-5.6 Pro consult takes 20–60 minutes of wall clock — wait for it; the session log is the durable record.
    oracle --engine browser -p "$(cat consult-prompt.md)" \
      --file "src/**/*.ts" --slug "<three-to-five-word-slug>"

Success check: a response was received and recorded. The handshake and your consult both appear as sessions:

oracle status --hours 24
🧿 oracle 0.9.0 — AI confidence filtered through reality.
Recent Sessions
Status    Model         Mode    Timestamp           Chars    Cost  Slug
completed gpt-5.6-pro   browser 07/16/2026  9:34 AM  4532       -  <your-consult-slug>
completed gpt-5.6-pro   browser 07/16/2026  9:02 AM   212       -  hi

Attachments — the Oracle skill family

These are the presenter's real skill files, verbatim — the same six skills that drive everything on this page: oracle (the maximum-batch consult contract, plus its packx references and round-robin scripts), oracle-execute (Oracle-planned execution loops), oracle-schedule (one scheduled future consult), oracle-video (the Gemini video pipeline, with its repeatable follow-up process), oracle-video-create (Gemini video generation), and imagine (ChatGPT image generation).

They orchestrate Oracle's browser engine plus packx and assume the presenter's accounts and setup — the round-robin pieces are pinned to one private pool you don't have. Install them to study and adapt to your own accounts, not to run unmodified. One block downloads all six into a staging folder and installs them into the current project. Two verified gotchas baked in: .md files must be fetched with ?raw (the bare URL returns an HTML viewer page), and the staging folder must not be named skills/ — the installer claims ./skills/ as one of its own targets and would clobber your downloads with empty symlinks.

BASE=https://shiny-rosette-m6zy.here.now/skills
D=oracle-skill-family
mkdir -p $D/oracle/references $D/oracle/scripts $D/oracle-execute \
  $D/oracle-schedule/agents $D/oracle-video/references \
  $D/oracle-video-create $D/imagine/agents
curl -fsS "$BASE/oracle/SKILL.md?raw" -o $D/oracle/SKILL.md
curl -fsS "$BASE/oracle/references/round-robin-receipt.md?raw" -o $D/oracle/references/round-robin-receipt.md
curl -fsS "$BASE/oracle/references/round-robin-transport.md?raw" -o $D/oracle/references/round-robin-transport.md
curl -fsS "$BASE/oracle/references/packx-quick-reference.md?raw" -o $D/oracle/references/packx-quick-reference.md
curl -fsS "$BASE/oracle/references/packx-deep-reference.md?raw" -o $D/oracle/references/packx-deep-reference.md
curl -fsS "$BASE/oracle/scripts/extract_codex_conversation.py" -o $D/oracle/scripts/extract_codex_conversation.py
curl -fsS "$BASE/oracle/scripts/run_round_robin.sh" -o $D/oracle/scripts/run_round_robin.sh
curl -fsS "$BASE/oracle-execute/SKILL.md?raw" -o $D/oracle-execute/SKILL.md
curl -fsS "$BASE/oracle-schedule/SKILL.md?raw" -o $D/oracle-schedule/SKILL.md
curl -fsS "$BASE/oracle-schedule/agents/openai.yaml" -o $D/oracle-schedule/agents/openai.yaml
curl -fsS "$BASE/oracle-video/SKILL.md?raw" -o $D/oracle-video/SKILL.md
curl -fsS "$BASE/oracle-video/references/repeatable-video-followup-process.md?raw" -o $D/oracle-video/references/repeatable-video-followup-process.md
curl -fsS "$BASE/oracle-video-create/SKILL.md?raw" -o $D/oracle-video-create/SKILL.md
curl -fsS "$BASE/imagine/SKILL.md?raw" -o $D/imagine/SKILL.md
curl -fsS "$BASE/imagine/agents/openai.yaml" -o $D/imagine/agents/openai.yaml
chmod +x $D/oracle/scripts/extract_codex_conversation.py $D/oracle/scripts/run_round_robin.sh
npx skills add ./$D --skill '*' -y

To install just one skill instead of all six, change the last line — for example npx skills add ./oracle-skill-family --skill oracle -y.

Where the strongest models live

The easy assumption is that maximum intelligence is an API call away. It isn't. ChatGPT's strongest tier — the model picker's "Latest" row, currently GPT-5.6 Pro with Extended thinking — is a subscription feature of the chat product. And Gemini's video understanding is only reachable through the page's own upload widget; the API path can't upload the browser video at all. The strongest text model and the only real video-watching path both sit behind logged-in chat sessions. Whoever holds a valid session cookie holds the key.

How Oracle borrows your browser

The whole mechanism in one breath: a human signs into ChatGPT in normal Chrome once; Oracle copies those session cookies into a temporary automation profile; the agent then drives that profile like a very fast reader who pastes a huge bundle of code and waits. What rides along with the cookies is context — bundles validated up to roughly 900k tokens of project code per consult.

The contrast that makes it click: an API integration authenticates as a program and gets program-shaped limits. A cookie-borrowing browser authenticates as you and gets everything the chat product gives you — the model picker, extended thinking, and the file-upload widget the video pipeline depends on.

Most people run this on their own laptop, and that is the whole setup. One operator's variant: an always-on Mac mini runs oracle serve with the signed-in Chrome, every other machine points at it over a private network, and a four-slot dual-account pool runs four hour-long consults at once while nobody's laptop stays open. Same trick, made multi-tenant.

What 1,978 real consults look like

A consult costs 20–60 minutes of wall clock, so the prompt contract bans spending it like a chat message. On 2026-07-16 the local archive held about 1,978 session folders shaped by that rule. A sample:

actions-parent-lifecycle-third   iteration 3 of a 12-iteration hardening audit
agent-chat-angle-one/-two/-three one commit verified from three independent angles
agent-chat-final-review          a fourth consult judging the three-angle panel
actions-popup-scrollbar-fix      forensic hunt for a scrollbar bug from a user report
agenda-fresh-redesign            full redesign plan for a slide-generating repo
loopcraft-segmentation-review    GPT-5.6 Pro planning the video pipeline below

The recurring shapes: iteration audits, where a fresh frontier reviewer re-reads the codebase every loop; multi-angle panels, where the same question runs three ways and a judge consult picks the winner; and pipeline-planning-the-pipeline — GPT-5.6 Pro designed the video sharding strategy that Gemini then executed. Every session leaves output.log and token receipts, replayable with oracle session <id> --render.

The Loop Craft rip: 93 minutes of video into a permanent wiki

On 2026-07-14 the ask was: take a public 93:49 YouTube workshop on building durable autonomous agents and build it into an extensive published wiki with resources, pull quotes, and copy-paste prompts. The run shows the discipline that makes fragile browser automation dependable.

First, probes. Early upload probes errored; a rebuild fixed the path; then the awaited-upload probe came back with the exact line ATTACHED_VIDEO_OK loopcraft-awaited-upload-probe — from the real MP4. Only then did the expensive runs start. GPT-5.6 Pro reviewed the segmentation plan, and Gemini watched source-native shards one by one, each analysis ending in its exact sentinel. The analyses prove Gemini genuinely watched: it heard "we are going to talk about Loopcraft…" and identified the GitHub workshop page with the presenter's picture-in-picture at the 00:30 mark.

Shard 004 is the teachable failure. It errored twice while its three siblings sailed through — which rules out "the pipeline is down" and points at the input. An exact re-encode fixed it completely: the analysis finished in 73 seconds with the exact sentinel, and the re-encode settings were kept as the durable media recipe for future runs. Classify the failure, change one variable, re-run the cheap proof, keep the fix.

The result is public and permanent: the Loop Craft workshop wiki and its video companion. A 93-minute recording became a quotable artifact in one working session — and after publishing, the agent curled the live URLs rather than trusting the publish receipt.

Appendix

Limits & caveats
  • Browser automation is experimental and most stable on macOS. UI drift, model-picker changes, and upload races are real — the probe discipline exists because this path breaks. On Linux, pass --browser-chrome-path/--browser-cookie-path if detection fails.
  • Cookie-based automation authenticates as your personal account. The sources describe capability and access, not permission: they do not analyze provider terms of service or account risk. Decide that trade-off for your own accounts.
  • The four-slot dual-account pool is qualified against one exact build and topology. There is no evidence it transfers to other machines or accounts without redoing that qualification. Its access tokens are private and absent from this entire site; the attached skill files describe the pool only via a generic ssh alias, loopback ports, and a pinned build hash — identifiers of the presenter's setup, useless without it.
  • "A consult repays the hour" is the contract's premise, not a measured result — the archive shows scale and shape of use, not a controlled comparison against cheaper prompting.
  • The Loop Craft timeline is compressed; some intermediate error attempts are omitted, and the full receipts stay in local session folders. The shard-004 re-encode is an empirical fix, not a diagnosis of why the original encoding failed.
  • The session archive figures (~1,978 folders) were counted on 2026-07-16 and grow continuously.
Provenance

Sources, all local records of one operator, re-verified 2026-07-16: the Oracle fork's README (browser-mode setup, handshake command, oracle serve); the oracle consult skill contract (maximum-batch rule, ~900k-token bundle target, browser-only transport); the round-robin transport reference (described structurally only); the oracle-video skill contract (Gemini pipeline, probe and sentinel discipline); metadata of ~1,978 consult session folders; the Loop Craft run of 2026-07-14 (session receipts, probe prompts, shard prompts, re-encode fix); and the two live published pages, fetched with HTTP 200 on 2026-07-16.

The maximum-batch consult prompt is the real session pattern with project-specific content replaced by declared <angle-bracket> slots; its two closing paragraphs are verbatim from the skill contract. The probe prompt generalizes one real probe's slug; the shard prompt is verbatim from the run's receipts. Private material — hostnames, ports, tokens, build hashes, absolute paths — is replaced with placeholders throughout the page prose. The downloadable skill files under skills/ are byte-identical copies of the presenter's real skill sources, taken and privacy-audited 2026-07-17 (no tokens, credentials, or absolute private paths; the round-robin pool appears only as a generic ssh alias and loopback ports). This page supersedes the earlier Scholarly Folio at this URL; its caveats moved here, intact.