revfactory/codex-harness

Latest recorded source activity: September 24, 2026 at 02:44

SkillsMP catalog refreshed: November 5, 2026 at 19:57

skills collected: 2

GitHub stars: 62
GitHub forks: 17

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/revfactory/codex-harness.

Repository README

Repository README source: README.md

Read the source README

Expand full README

<p align="center"> <img src="codex-harness.png" alt="Codex Harness robot mascot with coding tools" width="800"> </p> <p align="center"> <a href=".codex-plugin/plugin.json"><img src="https://img.shields.io/badge/Version-0.1.0-brightgreen.svg" alt="Version 0.1.0"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" alt="Apache 2.0 License"></a> <img src="https://img.shields.io/badge/Codex-Plugin-purple.svg" alt="Codex Plugin"> <img src="https://img.shields.io/badge/Patterns-6_Architectures-orange.svg" alt="6 Architecture Patterns"> <img src="https://img.shields.io/badge/Mode-Subagents-green.svg" alt="Codex Subagents"> <a href="https://github.com/revfactory/codex-harness/stargazers"><img src="https://img.shields.io/github/stars/revfactory/codex-harness?style=social" alt="GitHub Stars"></a> </p> # Harness for Codex **English** | [한국어](README_KO.md) | [日本語](README_JA.md) A project-scoped harness factory for Codex. It inspects a project, designs a small team, and creates native Codex agents and reusable skills. A parent orchestrator schedules independent tasks in parallel, integrates the results, and owns final verification. This is an independent migration of [revfactory/harness](https://github.com/revfactory/harness), based on upstream commit [`cceac68`](https://github.com/revfactory/harness/commit/cceac68ea1d0ad198ef4b7b906cd238375836387). The original project's team-design workflow and six architecture patterns are adapted to Codex. Upstream Claude Code benchmarks do not establish performance for this migration. ## Install as a plugin (recommended) Run these two commands in your terminal. You do not need to clone this repository or run the Python installer: Add Marketplace ```bash codex plugin marketplace add https://github.com/revfactory/codex-harness.git ``` Add Plugin ```bash codex plugin add codex-harness@codex-harness ``` Open **your target project in a new Codex session**, then send: ```text $harness Write a short blog post about organizing a new project and save it to article.md. ``` Explicitly invoking `$harness` (or `$codex-harness:harness`) builds or updates a durable harness in the **current target project by default**, even when the rest of the request is an ordinary content task. It then performs that task. An explicit read-only request or instruction not to build a harness takes precedence. Agent definitions live under the target project's `.codex/agents/*.toml`; reusable skills live under `.agents/skills/`. The harness adds an `AGENTS.md` pointer, project configuration, and run records as appropriate. When Codex is started in the target project, native agents work there rather than in the plugin cache. Plugin installation alone creates no project files. The optional [project installer](#install-into-another-project-optional) supplies the predefined five-role team; invocation chooses roles for the actual project. Start Codex in that project (`codex -C /absolute/path/to/project`) before using its agents: native spawn has no `cwd` parameter and inherits the parent project's session directory. If the current session started elsewhere, bootstrap files can be written in the target with an explicit workdir, but start a fresh session in the target before spawning agents. See [quickstart troubleshooting](docs/quickstart.md#troubleshooting) for protected-directory write failures. The command syntax above was checked against Codex CLI **0.153.4**. After adding the marketplace, you can also use `/plugins` in the CLI to select **Codex Harness → Harness for Codex → Install**, then start a new session. See [quickstart](docs/quickstart.md#install-as-a-plugin-recommended) for desktop installation, a local-checkout option, and troubleshooting. [Official plugin guide](https://learn.chatgpt.com/docs/plugins). ## Start in this checkout (for development) Clone the repository: ```bash git clone https://github.com/revfactory/codex-harness.git cd codex-harness ``` Open this directory as a trusted local project in a **new Codex session**, then send: ```text $harness Build a harness for this project. Use subagents in parallel for independent tasks. ``` Korean also works: ```text $harness 이 프로젝트에 맞는 하네스를 구성해줘. 독립 작업은 서브에이전트로 병렬 처리해줘. ``` Project agents and the `harness` skill are already in this checkout. If newly generated agents are absent from the current session, start a new thread in the project. See [quickstart](docs/quickstart.md) for installation into another project and a live smoke test. ## Install into another project (optional) Requires Python 3.11+; the scripts use only the standard library. Run from this checkout: ```bash python3 scripts/install.py --target /absolute/path/to/project --dry-run python3 scripts/install.py --target /absolute/path/to/project python3 scripts/validate.py --project /absolute/path/to/project ``` The installer copies the canonical `harness` skill and five seed agents, and merges supported project configuration forms and the `AGENTS.md` pointer while preserving existing content. This predefined scaffold is optional; explicit skill invocation builds a project-specific harness without it. Review any reported conflicts. An inline `agents = { ... }` table that needs missing defaults may require expansion to `[agents]`; the installer reports this before writing files. It does not change personal Codex configuration. Open the target in a new trusted local Codex session after installation. The [Codex plugin manifest](.codex-plugin/plugin.json) packages the skill from the standard `skills/` directory. The [repository marketplace](.agents/plugins/marketplace.json) makes it installable as `codex-harness@codex-harness`. Plugin installation alone does **not** create project files; explicit invocation builds the project-specific harness, while the project installer supplies the optional predefined scaffold. ## How the team works | Role | Responsibility | Configured sandbox | | --- | --- | --- | | Parent session | Scheduling, shared interfaces, integration, final acceptance | Current session | | `harness_explorer` | Map relevant code and return cited evidence | Read-only | | `harness_architect` | Plan boundaries, dependencies, and acceptance criteria in its response | Read-only | | `harness_worker` | Implement within explicitly owned files | Workspace-write | | `harness_reviewer` | Report actionable defects without editing | Read-only | | `harness_qa` | Execute checks; write assigned tests and verification artifacts | Workspace-write | The parent assigns each task an objective, owned files, dependencies, and acceptance criteria. Workers share a workspace, preserve each other's edits, and return evidence. Shared files have one owner; dependent tasks wait for their inputs. The parent closes or reuses completed agents and handles capacity limits without dropping work. The project config enables native subagents and requests at most **three concurrent subagent threads**; the parent session coordinates them. Runtime limits may reduce available capacity. Models and reasoning effort inherit from the parent. Child agents do not recursively delegate by default. QA's prohibition on product edits is an instruction boundary within its write-enabled sandbox. See [multi-agent design](docs/multi-agent.md) for the full protocol and sandbox caveats. ## Layout ```text AGENTS.md Project entry point .codex/config.toml Project subagent settings .codex/agents/*.toml Five native seed agents skills/harness/ Single physical skill source SKILL.md Canonical harness-building workflow references/ Patterns, handoffs, examples, QA guidance scripts/create_agent.py Create a project agent safely scripts/validate.py Structural and run completion validation scripts/run.py Run state, refreshed context, agent lifecycle scripts/communication.py Explicit collaboration event log .agents/skills/harness Symlink → ../../skills/harness .codex-plugin/plugin.json Plugin manifest; skills = "./skills/" .agents/plugins/marketplace.json Installable repository marketplace scripts/install.py Install into a target project scripts/validate.py Repository validation entry point tests/ Automated installer and validation checks docs/ Usage, architecture, migration, compatibility .harness/runs/<run-id>/ Runtime plans, packets, results, agent registry _workspace/communications/ Explicit message JSONL logs and optional exports ``` In this checkout, `.agents/skills/harness` links to `skills/harness` for project discovery, so the plugin and project use one source. The installer follows that alias and copies regular files into the target project's `.agents/skills/harness/`; the installed project needs no symlink. The six design patterns remain available: pipeline, fan-out/fan-in, expert pool, producer/reviewer, supervisor, and hierarchical decomposition. Hierarchical decomposition becomes a parent-managed dependency graph; it does not require recursive agent spawning. ## Run state and agent communication The shell examples below use paths created by explicit `$harness` invocation or the optional project installer. Before invocation, a plugin-only installation keeps those helpers in the installed skill directory. The parent initializes a run from an actual project plan, records native agent IDs, and gives each child a refreshed packet with the project root, stable input fingerprints, decisions, skills, ownership, dependencies, and acceptance criteria. Related follow-ups can reuse the same agent; independent reviews can use fresh context when the runtime supports it. Models and the three-subagent concurrency setting stay inherited/configured as above. ```bash python3 .agents/skills/harness/scripts/run.py --project . init \ --plan-file /absolute/path/to/project-plan.json --run-id project-v1 python3 .agents/skills/harness/scripts/run.py --project . ready --run project-v1 python3 .agents/skills/harness/scripts/run.py --project . status --run project-v1 ``` Workers proactively share findings, ask focused questions, answer peers, and announce dependency readiness and handoffs. The parent confirms contracts and ownership. Important messages are explicitly logged under `_workspace/communications/<run-id>.jsonl`: record the outward event, use the actual native messaging tool, then record its delivery outcome and correlate replies. Read-only roles ask the parent to log and route their messages. Local logging does not send messages or automatically capture Codex internals. ```bash python3 .agents/skills/harness/scripts/communication.py --project . --run project-v1 view \ --format markdown --output _workspace/communications/project-v1.md python3 .agents/skills/harness/scripts/validate.py --project . --run project-v1 --complete ``` Task completion is separate from native session idleness or termination. Before transferring write ownership, the parent confirms the previous agent has stopped or is idle. On resume, changed inputs/results and affected dependent tasks are invalidated. Use ordinary `resume` when only existing input file contents change. For changed decisions, ownership, acceptance criteria, objective, or added/removed tasks, supply a revised template without editing the old run ledger: ```bash python3 .agents/skills/harness/scripts/run.py --project . resume \ --run project-v1 --new-run project-v2 \ --plan-file /absolute/path/to/revised-project-plan.json ``` Changed contracts and affected descendants become pending; unchanged accepted work can be reused. Product fixes belong to workers; QA verifies the corrected behavior. See the [runtime guide](skills/harness/references/runtime-guide.md) for plan/result schemas, exact commands, and message correlation. ## Verification ```bash python3 scripts/validate.py --project . python3 -m unittest discover -s tests -v ``` For an optional live test, run from this checkout with an authenticated Codex client. Choose a new target directory: ```bash python3 scripts/live_smoke.py run --target _workspace/live-tests/NEW_ID ``` The script exercises two native custom workers, a blocked task and failed completion check, an input correction followed by resume and reuse of the unchanged result, then two QA assertions. It allows up to 1,200 seconds and is excluded from default CI. Inspect its actual transcript, files, and check results; the command itself is not a recorded pass. **97 automated tests passed**. A repeated-resume correction preserves ancestor outputs; its [verification summary and two unresolved cross-run limitations](docs/verification/resume-provenance-2026-09-17/README.md) are recorded separately. A separate **Codex CLI 0.153.4 run used two native custom workers and an independent QA agent** to verify file creation, peer communication records, a blocked completion, partial resume, unchanged-result reuse, and passing final tests. See the [verification record](docs/verification.md) for evidence and limits, including the earlier read-only smoke and observed ephemeral-session issue. Other clients, sandbox enforcement, and performance were not benchmarked. Repeat the live regression above in your environment. - [Quickstart](docs/quickstart.md) - [Multi-agent architecture and task packets](docs/multi-agent.md) - [Claude Code → Codex migration](docs/migration.md) - [Codex compatibility](docs/compatibility.md) - [Service migration starter example](examples/service-migration/README.md) - [Contributing](CONTRIBUTING.md) ## License and attribution [Apache License 2.0](LICENSE). Original Harness by the contributors to [revfactory/harness](https://github.com/revfactory/harness). This migration retains the upstream license; its Codex behavior and verification status are documented separately from upstream releases.

Loading the repository README…

Skills in this repository

Software Developers

1 occupation category · 50% classified

skill

occupation

description

updated

harness

unclassified

Codex용 프로젝트 하네스를 구축·마이그레이션·확장·점검하는 메타 스킬. `$harness` 또는 `$codex-harness:harness`를 명시적으로 호출하면 함께 요청한 조사·글쓰기·코드 작업이 일반적인 표현이어도 대상 프로젝트에 지속 가능한 하네스를 기본 구축·갱신한다. 명시 호출이 없는 일반 작업이나 개념 질문만으로 새 하네스를 만들지 않는다. 명시적인 읽기 전용·감사 요청은 그 범위를 따른다.

Source text: Korean

2026-09-24

service-migration

Software Developers

서비스 API의 응답 계약과 클라이언트 소비 코드를 함께 마이그레이션한다. 응답 래핑·필드 이름 변경, 소비 코드 동기화, 기존 마이그레이션 수정·보완·부분 재실행에 사용한다. 단순 UI 스타일 수정이나 API 개념 설명에는 사용하지 않는다.

Source text: Korean

2026-09-07

Showing 2 of 2 collected skills.