메뉴
Openharness is an open-source harness for structured LLM evaluation and capability benchmarking. Registered as an external reference to inform OctoCode's evaluation-gate design (see docs/eval/*) and the benchmark gate in runtime/src/benchmarks.rs.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when: applying Matt Pocock engineering skills for diagnosis, TDD, architecture improvement, issue breakdown, PRD creation, or rigorous TypeScript/codebase analysis.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
Use when: working with OpenAI Codex plugins, plugin marketplaces, plugin manifests, plugin-bundled skills, or the openai/plugins repository. Helps inspect .codex-plugin/plugin.json, .agents/plugins/marketplace.json, and installed Codex plugin cache.
| name | openharness |
| description | Openharness is an open-source harness for structured LLM evaluation and capability benchmarking. Registered as an external reference to inform OctoCode's evaluation-gate design (see docs/eval/*) and the benchmark gate in runtime/src/benchmarks.rs. |
| source | https://github.com/openai/openharness |
| integration | external-benchmark |
| status | descriptor-only |
Descriptor-only registration (P12 batch). Openharness provides a reproducible harness for running LLM capability benchmarks across tasks and scoring them deterministically.
check_regression in crates/octocode-runtime/src/benchmarks.rs) with an absolute floor to tame sub-millisecond jitter; pairing with a capability harness closes the loop on "does the model still reason?" in addition to "is the runtime still fast?".octocode-cli bench --harness openharness subcommand.integrations.openharness.task_dir setting.openharness task outputs through the existing event_feed_json so WebUI can display runs.OCTOCODE_ALLOW_BENCH=1.Benchmarks may invoke external providers; treat quota and key exposure the same as any LLM call. Do not run against production providers from CI without explicit operator approval.