Run the great_cto controlled Codex lifecycle with controller-owned writes, verifier evidence, human gates and optional artifact release.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Use the version-pinned npm entrypoint below. A Codex plugin install loads skills
and MCP configuration, but it does not add the great-cto npm binary to PATH.
Do not imitate Claude Code hooks or manually chain roles: the controller reads
shared/pipeline.toml, persists the cursor and owns every write and gate
transition.
npx --yes great-cto@3.64.0 codex-host doctor
npx --yes great-cto@3.64.0 codex-host list --dir /absolute/project
doctor.state=blocked means do not start. Docker may be unavailable when no
checks/release policy is requested; GitHub CLI may be unavailable when the local
adapter is used. The run store must not be group/world accessible.
For mixed-host runs, also require doctor.checks.claude.state=available.
Policies must be operator-owned absolute files outside the worker project. Allowed paths are explicit controller write boundaries.
npx --yes great-cto@3.64.0 codex-host start \
--dir /absolute/project \
--prompt "the requested outcome" \
--allow src,tests,docs \
--checks-policy /absolute/operator/checks.json \
--release-policy /absolute/operator/release.json
Read the returned status, pending and release object. Never treat exit 2 as
success: it means a gate, manual action or blocked evidence requires attention.
Since 3.47.0, independent
graph roles can run on both hosts with
--routes qa-engineer=claude-code,security-officer=codex on start. The
controller dispatches only a symmetric join pair concurrently, checks both
proposals for overlap, serializes writes and runs the existing verifier and
human gates. The route map is fixed for the run. An interrupted wave must be
inspected; never start replacement workers against an uncertain wave.
Show the operator the exact gate/release summary and wait for explicit approval. Then pass back the controller-issued token; never synthesize or persist one in a project file.
npx --yes great-cto@3.64.0 codex-host approve RUN_UUID --token GATE_TOKEN
npx --yes great-cto@3.64.0 codex-host approve-release RUN_UUID --token RELEASE_TOKEN
npx --yes great-cto@3.64.0 codex-host resume RUN_UUID
Use recover only after inspecting the recorded reason. Recovery reuses the
same candidate and refuses unknown partial writes. cancel revokes unexecuted
approval but does not delete external audit evidence.
The local and GitHub Release adapters publish immutable artifacts and declare
activation: none. They do not deploy traffic. Local rollback means selecting
a previous directory; GitHub rollback is a newly gated superseding release.
Production activation needs a separate adapter and approval contract.
Detailed policy schemas and limitations are in docs/HOST-CODEX.md.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
great_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two faces divided by MEANING (Geist speaks, Geist Mono is machine-truth), tabular numerals, and a dash that is not a nought. Twelve checkable rules measured from packages/board and greatcto.systems, not designed for this file. Use when building or extending any great_cto surface — the board, the site, a report, a share page.
中文简介正在准备中。当前显示原文说明。
Catalogue of known SDLC anti-patterns that great_cto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
中文简介正在准备中。当前显示原文说明。
Analyze images, websites, and Figma files to extract their design and generate a `design.md` with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest reference, a mockup, a competitor's site, a component, a dashboard, a landing page. Also when they ask 'extract the design system from X', 'document the style of Y', 'analyze this visually', 'convert this image into tokens', 'help me replicate this design', 'what palette does this site use', 'how is this built'. Also for single elements: 'copy this navbar', 'recreate this illustration', 'give me a prompt to regenerate this graphic' — element mode outputs a focused element.md, with token-grounded image-model prompts when the element is visual art. If the user brings any visual source and wants to understand it at a design level — this skill should activate.
中文简介正在准备中。当前显示原文说明。
Shared review framework that every domain reviewer (pci, oracle, gov, edtech, healthcare, mlops, etc.) MUST follow. Defines the output artifact (TM-{slug}.md), mandatory sections, severity scale, verdict format, the workflow scaffold (when-invoked, Step-0 read-inputs, HANDOFF), and the "domain heuristic vs generic check" boundary. Eliminates duplication across the ~30 reviewer prompts.
中文简介正在准备中。当前显示原文说明。
Structured idea generation + multi-LLM debate for the product-owner stage. Diverge (generate genuinely different bets), debate (a 4-persona panel on 4 models argues over 2 rounds), converge (synthesize a recommendation). Used by product-owner before architect; available to architect for design-space exploration.
中文简介正在准备中。当前显示原文说明。
How to write — and how to use — a skill that IS one aesthetic rather than a catalogue of them. A catalogue lets an agent pick, and it picks the modal option; a committed aesthetic makes it execute one thing precisely, against rules you can check. Use when a design keeps coming out competent and forgettable, when starting a new brand surface with no reference, or when authoring a house style you want executed the same way twice.
中文简介正在准备中。当前显示原文说明。