Section 00

Workshop Workflow Index

Use this as the map for the full workflow. Each section stands alone, but the sequence is deliberate.


setup agent prompt
Use this workflow index to choose the next agent move for a software project.

First identify the current bottleneck:
- missing context
- missing shell tools
- unclear helper behavior
- wrong workspace or session
- weak prompt shape
- too many plausible implementations
- video or runtime evidence to analyze
- bounded debug packet to preserve
- narrow task to delegate
- risky decision that needs independent model critique
- generated options that need a human pick

Then pick the matching section and ask the agent to follow that workflow. Keep the request concrete: name the repo, the bug or decision, the files or logs to inspect, and the proof you expect before the work is considered done.

Workflow route

Workshop Workflow Index

Use this as the map for the full workflow. Each section stands alone, but the sequence is deliberate.

Eggo locks the main route map before the branches scatter for the Workshop Workflow Index workflow, making the page's operating move visible.
Intent

Name the software-workflow decision before launching work.

Evidence

Inspect the file, command, log, prompt, or recording that proves the state.

Route

Pick the narrow agent, tool, shell, or council path that matches the problem.

Verify

Confirm the result with output, screenshots, receipts, or saved decisions.

  1. Phase Map
  2. Section Map
  3. How To Use The Set
one path is aligned while loose section cards stop drifting

Phase Map

Phase 1: Context And Environment

Make invisible project context and agent shell context explicit before asking for work.

  1. Pack context when broad code reasoning needs Oracle.
  2. Make the shell and tools visible to Codex.
  3. Classify zsh helper names and fallback boundaries.

Transition: Once the agent can see the right context and tool surface, route the work to the right place before launch.

Phase 2: Routing And Composition

Put work in the right workspace, pane, session, and prompt shape before it runs.

  1. Route the right pane/session.
  2. Compose before launch.

Transition: Once launch is deliberate, use the agent surface to produce, compare, and preserve evidence.

Phase 3: Generation And Evidence

Generate useful options and turn rich runtime or media evidence into prompt material.

  1. Generate verified variations.
  2. Use video as prompt material.
  3. Mark debug moments with bounded evidence.

Transition: Once the work is bounded and evidenced, delegate narrow packets or ask for independent review.

Phase 4: Delegation And Review

Hand small tool-shaped work to narrow agents, use councils for expensive decisions, and capture human choices before implementation.

  1. Hand tool-shaped packets to narrow Imps.
  2. Ask a model council when independent disagreement improves a risky decision.
  3. Capture a phone-friendly human selection from generated options and resume from saved JSON.

Section Map

PhaseSectionWorkflow MoveFile
Context And Environment1Pack context when broad code reasoning needs Oracle01-oracle-packing-context.md
Context And Environment2Make the shell and tools visible to Codex02-loading-zsh-env-into-codex.md
Context And Environment3Classify zsh helper names and fallback boundaries03-zsh-functions-aliases.md
Routing And Composition4Route the right pane/session04-agentic-dev-environment-orchestrator.md
Routing And Composition5Compose before launch05-prompt-builder.md
Generation And Evidence6Generate verified variations06-code-is-free-generate-variations.md
Generation And Evidence7Use video as prompt material07-video-as-prompts.md
Generation And Evidence8Mark debug moments with bounded evidence08-debugging-with-agent-markers.md
Delegation And Review9Hand tool-shaped packets to narrow Imps09-imps.md
Delegation And Review10Ask a model council when independent disagreement improves a risky decision10-fusion-model-council.md
Delegation And Review11Capture a phone-friendly human selection from generated options11-web-choices.md

How To Use The Set

Start with the section that matches the current bottleneck:

BottleneckStart With
The agent needs a broad codebase answerSection 1
A command works locally but not in CodexSection 2
A helper name is unclear or shell-onlySection 3
Work is landing in the wrong pane or sessionSection 4
The prompt needs shaping before launchSection 5
Several implementations are plausibleSection 6
A recording contains the missing contextSection 7
Logs exist but the important moment is unclearSection 8
The task is mostly one command-line toolSection 9
Several strong models may disagree on a risky architecture or implementation choiceSection 10
The agent generated good options but needs a human pick or feedback before continuingSection 11

Section 10 is especially useful after Section 6 for comparing strategies, or after Section 9 when a bounded packet needs independent review before a risky implementation choice. Section 11 is especially useful after Section 6 or Section 10 when generated options need a human selection, ranking, or feedback before implementation continues.