Evolve specs through guided interviews
Run Socratic questioning loops to clarify ambiguity in requirements before execution, feeding each evaluation back into refined specifications.
# Ouroboros - Development Environment > This AGENTS.md is for local development only . End users install via: > > Codex plugin marketplace add Q00/ouroboros > Codex plugin add ouroboros@ouroboros > > Once installed as a plugin, skills/hooks/agents work natively without this file. ## ooo Commands (Dev Mode) When the user types any of these commands, read the corresponding SKILL.md file and follow its instructions exactly: | Input | Action | |-------|--------| | ooo (bare, no subcommand) | Read skills/welcome/SKILL.md and follow it | | ooo auto ... | Read skills/auto/SKILL.md and follow it | | ooo interview ... | Read skills/interview/SKILL.md and follow it | | ooo seed | Read skills/seed/SKILL.md and follow it | | ooo run | Read skills/run/SKILL.md and follow it | | ooo evaluate or ooo eval | Read skills/evaluate/SKILL.md and follow it | | ooo evolve ... | Read skills/evolve/SKILL.md and follow it | | ooo unstuck or ooo stuck or ooo lateral | Read skills/unstuck/SKILL.md and follow it | | ooo status or ooo drift | Read skills/status/SKILL.md and follow it | | ooo ralph | Read skills/ralph/SKILL.md and follow it | | ooo tutorial | Read skills/tutorial/SKILL.md and follow it | | ooo setup | Read skills/setup/SKILL.md and follow it | | ooo welcome | Read skills/welcome/SKILL.md and follow it | | ooo cancel | Read skills/cancel/SKILL.md and follow it | | ooo qa or ooo qa ... | Read skills/qa/SKILL.md and follow it | | ooo help | Read skills/help/SKILL.md and follow it | | ooo update | Read skills/update/SKILL.md and follow it | | ooo pm or ooo pm ... | Read skills/pm/SKILL.md and follow it | | ooo brownfield or ooo brownfield ... | Read skills/brownfield/SKILL.md and follow it | | ooo publish or ooo publish ... | Read skills/publish/SKILL.md and follow it | | ooo resume-session | Read skills/resume-session/SKILL.md and follow it | Important : Do NOT use the Skill tool. Read the file with the Read tool and execute its instructions directly. ## Agents Bundled agents live in src/ouroboros/agents/ . When a skill references an agent (e.g., ouroboros:socratic-interviewer ), read its definition from src/ouroboros/agents/{name}.md and adopt that role. Use OUROBOROS AGENTS DIR or .Codex-plugin/agents/ only for explicit custom overrides. <!-- ooo:START --> <!-- ooo:VERSION:0.26.0 --> # Ouroboros — Specification-First AI Development > Before telling AI what to build, define what should be built. > As Socrates asked 2,500 years ago — "What do you truly know?" > Ouroboros turns that question into an evolutionary AI workflow engine. Most AI coding fails at the input, not the output. Ouroboros fixes this by exposing hidden assumptions before any code is written . 1. Socratic Clarity — Question until ambiguity ≤ 0.2 2. Ontological Precision — Solve the root problem, not symptoms 3. Evolutionary Loops — Each evaluation cycle feeds back into better specs Interview → Seed → Execute → Evaluate ↑ ↓ └─── Evolutionary Loop ─────┘ ## ooo Commands Each command loads its agent/MCP on-demand. Details in each skill file. | Command | Loads | |---------|-------| | ooo | — | | ooo auto | MCP: ouroboros start auto | | ooo interview | ouroboros:socratic-interviewer | | ooo seed | ouroboros:seed-architect | | ooo run | MCP required | | ooo evolve | MCP: evolve step | | ooo evaluate | ouroboros:evaluator | | ooo qa | ouroboros:qa-judge | | ooo unstuck | ouroboros:{persona} | | ooo status | MCP: session status | | ooo ralph | Persistent loop until verified | | ooo tutorial | Interactive hands-on learning | | ooo setup | — | | ooo help | — | | ooo update | PyPI version check + upgrade | | ooo publish | gh CLI — Seed to GitHub Issues | | ooo resume-session | Restore previous Codex session context | ## Agents Loaded on-demand
codex
Source: Q00 ↗graded C · 60/100 — how grades work →
More planning loops
Run flow until gate or timeout
Execute a flow step repeatedly until it signals DONE or GATE, or halt after 40 turns to proceed.
/goal FLOW says DONE or GATE, or stop after 40 turns then /flow-next
Looper — design-review your loop before running it
A plan-the-loop-first skill: it interviews you about the automation idea, previews the flow as ASCII art, and only writes final loop artifacts after you confirm — a safe on-ramp for loop beginners.
Skill interviews you about the automation idea, writes loop artifacts to `looper-output/`, shows an ASCII flow preview, and only finalizes after you confirm — design the loop before any runner touches files. Cap the run at 25 iterations; leave remaining work for the next session.
Draft a sprint plan from the backlog
Turn the open issue backlog into a proposed two-week sprint plan with estimates, a dependency ordering, and an explicit cut line, written as a document for the team to edit.
/goal SPRINT-PLAN.md contains a proposed 2-week plan — read all open issues labeled `ready`, estimate each as S/M/L based on the code it touches, order them by dependency and value, draw a cut line at a realistic capacity, and list what falls below it with reasons; make no changes to the issues themselves; stop after 6 turns
⧉ 1