「harness」の検索結果

Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method natively, with no claude_wrapper.py and no metered solver API.

日本語の概要は準備中です。原文の説明を表示しています。

xp-harness の skill / agent を新規作成・改修するとき、または xp-harness そのものの設計判断 (取り込む / 取り込まない / 翻訳する) を考えるときに必ず発火させる skill。xp-harness の中核思想 (最終形の理想像 = エージェント群と利用者で XP の開発チームを成す、価値で導きつつ規律装置最小注入、エンジニアとして振る舞う、ペアプロ哲学、中央集権より decentralized、outside-in 例外なし、対話と自走の境界、INVEST の取捨、共創を目指す対話) を context に inject し、新規 skill / agent の設計判断や既存 skill / agent の改修判断を、xp-harness 思想と整合させるためのもの。

Add regression test cases to the Bifrost provider harness (the Postman collection run via `make run-provider-harness-test`) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts them into tests/e2e/api/collections/provider-harness.json without reformatting the file, and validates via the augment and filter scripts. Invoked with /harness-test-writer <PR# | issue# | URL> or /harness-test-writer (prompts for a reference).

日本語の概要は準備中です。原文の説明を表示しています。

Evaluate a repo agent harness (AGENTS.md, rules, skills, skill refs) for broken paths/commands, redundant instructions, and usefulness using a stack-agnostic dual-judge protocol with planted traps. HIGH PRIORITY questionnaires at top: Q1 optional docs, Q2 B/C budget before Track A (certainty/tokens). A always runs after Q2; B/C opt-in. ADRs/RFCs excluded from T2. Mixed apply uses 11-mixed-apply.md (KEEP/CUT). Use when the user says harness eval, harness-eval, harness debug, audit AGENTS.md, audit skills/rules, instruction audit, redundancy of agent instructions, usefulness of skills, Ship/Review/Hold/Slim/Keep-core for harness, or wants Track A/B/C harness evaluation. Do NOT use for harness setup or init, feature spec-driven work (tlc-spec-driven), or applying Ship/Slim trims unless the user explicitly asks after the report.

日本語の概要は準備中です。原文の説明を表示しています。

Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method natively, with no claude_wrapper.py and no metered solver API.

日本語の概要は準備中です。原文の説明を表示しています。

Run a GEPA learning cycle via `metaharness learn` (upstream ADR-235, metaharness@0.3.0) — optimizes a harness genome against a SWE-bench-style slice manifest. $0 dry-run by default; `--run` is the explicit spend opt-in. Requires a metaharness repo checkout (`--repo` or $METAHARNESS_REPO) — without one it reports `checkout-required` with clone instructions. Degrades gracefully when metaharness is absent.

日本語の概要は準備中です。原文の説明を表示しています。

Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a vertical AI assistant for X".

日本語の概要は準備中です。原文の説明を表示しています。

Initialize a Harness Engineering framework in the current project. Use when user says 'harness', 'init harness', 'initialize framework', 'setup harness engineering', '/harness', or wants to set up a Plan-Build-Verify development workflow with specialized agents (planner, generator, evaluator). Creates CLAUDE.md, agent definitions, command templates, hooks, and documentation structure for autonomous AI-driven development.

日本語の概要は準備中です。原文の説明を表示しています。

LAM ハーネスの規範層をプロジェクトへ敷く初期化スキル。 plugin コンポーネントとして配れない層（.claude/rules/ と docs/internal/ と .claude/scripts/ = managed、 および CLAUDE.md 等の starter）をファイルとして配置し、.claude/harness.json に記録する。 ランタイム（Python）が無い環境では完了を拒む。 Layer 1（.claude/settings.json の permissions）は敷かず、手作業の手順として提示する。 Use when the user installs lam-harness into a project, or runs /lam-harness:init.

Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same mistake again, agent not improving, make agent smarter, agent quality plateau, agents ignore skills, agent skips tests, fix agent behavior, agent unreliable, improve agent setup, self-improving harness, agents worse over time, tune agent instructions, agent going in circles, agent ignores AGENTS.md, repeated agent errors. Requires harness v0 and eval harness. AUTO-ROUTED from harness-engineering on symptoms. Not first setup — harness-generation first.

日本語の概要は準備中です。原文の説明を表示しています。

Seed minimal agent harness v0 — manifest, eval checks stub, governance. AUTO-INVOKED after project-setup or retroactive-project-setup when docs/harness/manifest.json is missing. Also triggers on: generate harness, scaffold agents, agent bootstrap, first time agents in this repo, new project agent setup, set up agent harness, agent onboarding files, missing agent configuration, agent instructions setup, make agents read project rules, agent reliability setup, agents not configured. Pairs with project-setup. Evolution is harness-evolution.

日本語の概要は準備中です。原文の説明を表示しています。

Produce or apply an approved report-first proposal for workflow, ROSE, skill, command, subagent, memory, install, or harness-doc changes; use after harness-issue-triage localizes a harness problem or when the user explicitly requests harness maintenance, and do not edit core harness files without explicit human approval.

日本語の概要は準備中です。原文の説明を表示しています。

Run `@metaharness/darwin evolve {repo}` to mutate a harness's seven policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy), sandbox-score each variant, and promote only measured wins. The model is frozen; the harness evolves. Closes the loop ADR-150 opens (score+genome describe; evolve changes). Degrades gracefully when @metaharness/darwin is absent (ADR-150 + ADR-153 architectural constraints).

日本語の概要は準備中です。原文の説明を表示しています。

5-dimension harness readiness scorecard from `metaharness score {path}`. Returns harnessFit / compileConfidence / taskCoverage / toolSafety / memoryUsefulness + estCostPerRunUsd + scaffoldReady. Pure-read; subprocess invocation; degrades gracefully when MetaHarness is absent (ADR-150 architectural constraint).

日本語の概要は準備中です。原文の説明を表示しています。

The continual-harness refinement protocol — how an agent inspects its recent trajectory for failure signatures and improves its own harness (agent prompts, sub-agents, skills, memory) in place, mid-session, landing changes on the session branch immediately and promoting them to `main` only through a change request. Load this skill when a refinement prompt arrives mid-session, when the `harness-reflector` agent runs, or whenever you decide your own scaffolding needs repair. The sub-agent fan-out in this skill is for the top-level `harness-reflector` run only; if you loaded this as a subagent, do the four passes yourself and skip the fan-out.

日本語の概要は準備中です。原文の説明を表示しています。

Audit one or all supported agent harnesses (claude, codex, opencode, pi, omp, antigravity, cursor, grok) for config efficiency, hook overhead, permission friction, plugin and MCP cost, skill metadata portability, dead config, and measured session friction. Use when invoked as `$optimize-harness [harness ...] [focus]`, or when the user asks to optimize or compare agent harness configuration.

日本語の概要は準備中です。原文の説明を表示しています。

Research one agent harness's release (docs, source, runtime) and fill its capability cells in scripts/harness_capabilities.py with cited evidence. Use after a harness version bump, when just harness-probe reports re-research, or when capability cells read unknown.

日本語の概要は準備中です。原文の説明を表示しています。

Change the agent harness itself (AOS, AO or CBS hooks, gates, memory, permissions, delegation, plugins, bootstrap) the safe way: look up the matching harness pattern, design against its gotchas, build with /startcycle and a live trail, check every harness, open a PR after GO. Use for "change a hook", "fix the go-gate", "harness work", "plugin change".

日本語の概要は準備中です。原文の説明を表示しています。

大規模言語モデルの知識・推論・コード生成を共通の課題で評価するスキル。複数モデルの比較表や学習途中の成績推移を作り、評価結果と個別の回答を保存します。

• MMLU・GSM8Kでのモデル評価
• 複数モデルの比較表作成
• 学習途中のモデルの成績追跡

Inspect and audit GEPA genomes via the `@metaharness/darwin/gepa` library entry (darwin 0.8.0) — load/validate a genome (default is the shipped cand-6 promotion), render the system prompt a genome compiles to, or classify failure modes in a run transcript. The `gepaOptimize` loop itself is library-only (bring your own evaluator) and not surfaced here — use `harness-evolve` for sandbox-scored evolution. Degrades gracefully when @metaharness/darwin is absent.

日本語の概要は準備中です。原文の説明を表示しています。

Manage `@metaharness/darwin` bench suites — `bench create {repo}` scaffolds a JSON suite from a repo's test corpus; `bench verify {suite.json}` checks suite well-formedness. Bench suites are the fixed evaluation corpora that `harness-evolve --bench {suite.json}` scores variants against, decoupling evolution from the repo's natural tests. Degrades gracefully when @metaharness/darwin is absent.

日本語の概要は準備中です。原文の説明を表示しています。

Static security scan of a harness's declared MCP surface via `harness mcp-scan {path}`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch. Exits 1 on findings at or above `--fail-on` severity.

日本語の概要は準備中です。原文の説明を表示しています。

Run `@metaharness/darwin security bench` (upstream "Darwin Shield" / ADR-155) — evolves a champion security-detection harness against a 10-vuln / 9-decoy corpus and grades it on TPR/FPR/patch-pass/repro/unsafe vs four baselines (B0 static, B1 LLM-single-pass, B2 fixed-agent, B3 Darwin-champion). Closest reference implementation for ruflo's own ADR-155 nightly self-learning security harness (PR

日本語の概要は準備中です。原文の説明を表示しています。

Canonical reference for Kortix projects, Apps (sites, servers, backends with volumes) and internal business apps, the CLI, sessions, sandboxes, change requests, triggers, connectors, secrets, system skills, and the two session harnesses, pi and OpenCode. Covers `kortix.yaml` versions 1 and 2, serverless App deployments, harness configuration (`harnesses/pi/`, `harnesses/opencode/`), session identity, credential boundaries, and the complete pi and OpenCode references. Load when the user asks how Kortix works, what Kortix can do, how to deploy an App, how an agent discovers platform instructions, how to customize or configure this project's agents (create or fix an agent, subagent, skill, tool, plugin, extension, pi package, command, MCP server, model or permission rule; edit `opencode.jsonc`), how to edit `kortix.yaml`, how to use the `kortix` CLI, how to land work through a change request, or how to schedule and automate work.

日本語の概要は準備中です。原文の説明を表示しています。