「guard」の検索結果

Safety, privacy, cost management, and frank advice for building always-on AI agents with episodic memory. Covers data hygiene, privacy risk surfaces, runaway cost prevention, scope creep, psychological effects of persistent AI companions, and responsible deployment patterns. This is the skill that tells you what can go wrong and how to prevent it. Activate on: "agent safety", "always-on agent privacy", "agent cost control", "persistent agent risks", "AI companion safety", "agent data hygiene", "runaway agent costs", "parasocial AI risk", "/always-on-agent-safety". NOT for: architecture design (use always-on-agent-architecture), input design (use always-on-agent-inputs), application brainstorming (use always-on-agent-applications), healthcare compliance specifically (use hipaa-compliance).

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 read-only SQL against BigQuery public datasets with local result capture, cost safeguards, and reproducibility outputs.

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。

Guide pump setting adjustments for the MiniMed 780G system based on CareLink data, using Medtronic's 3-step follow-up workflow. Use when a clinician has CareLink data for a 780G patient and wants to know what to change — which setting, by how much, and how to program it. Triggers include: "what do I adjust", "how to fix high TIR", "how to reduce hypos", "adjust ICR/ISF/basal", "SmartGuard settings", "780G pump settings review", or any question about optimising 780G therapy after reviewing a download.

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。

Triage an incoming request — pick the workflow entry phase (intake / spec / tdd / chore) and record the workflow statefile that the Track Guard reads.

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。

Cycle-end retrospective converting recurring judgment failures into durable enforcement. Reviews the cycle's friction — repeated user corrections, guard trips, RCA themes, integrate failures — and turns each recurring one into a landmines.md entry, then proposes graduation candidates up the enforcement funnel (landmine → advisory hook → hard gate). Pairs with standup: standup says what shipped and what's next; retrospective says what kept going wrong and how to stop it structurally. Writes only memory entries and a report — graduation proposals are advisory and require the normal seed.md amendment path to become enforcement. Invoke at the end of a release cycle, an epic, or any stretch of work with repeated friction.

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。

Generate or repair a project's .gitignore. Composes the baseline must-ignore set (the single source of truth in baseline-ignores.json) with optional gitignore.io enrichment, and merges add-only so existing entries are never lost. Use when a repo has no .gitignore, when the commit-leak guard reports a gap, or when onboarding a new stack. Trigger: "set up gitignore", "fix my gitignore", "ignore node_modules/secrets", "gitignore for <stack>".

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。

Workflow Phase 11 — Commit Preparation and Execution. Stages and commits the work. Requires `/grant-commit` first (Git Commit Guard enforces a 15-min ad-hoc consent window; inside a workflow the grant is slug-scoped and one grant covers the whole landing).

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。

Design spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description.

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。

Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.

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。

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

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。

Review changed code for YAGNI, removable over-complexity, reuse, code quality, and efficiency, then apply worthwhile simplifications. Use when the user asks to simplify, clean up, tighten, de-hack recent changes, identify logic that can be dropped, or review whether added safeguards and edge-case handling are actually needed.

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。

Review database migration files for naming conventions and dangerous operations. Auto-activates for migration files.

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。

Let your agent shop online with guardrailed wallets, multiple payment methods, and owner 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。

Use when writing, debugging, or configuring an omp hook or extension — blocking or rewriting tool calls, redacting tool output, reshaping LLM context, registering tools/commands, or wiring modules through config.yml. Covers ExtensionAPI (current) vs HookAPI (legacy), the event catalog, discovery and load order, and disable controls. Not for Claude Code hooks (~/.claude/settings.json) or the shared harness safety guard (~/.agents/harness/hooks/).

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。

Read-only reviewer for agent-flow. Judges one diff against the acceptance criteria, AGENTS.md rules, protected paths and risk boundaries; returns a JSON verdict with line-anchored findings. Use when launched with AGENT_FLOW_ROLE=reviewer or asked for an agent-flow review of a diff.

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。

Manages brand identity, visual design system, and creative quality for MMIND.ai. Generates complete image prompts for Nano Banana Pro (Gemini), enforces the strict 5-color palette, flat-vector SaaS style, and typography standards. Use when user needs graphic prompts, brand consistency checks, visual style guidance, design briefs, or creative QA for any marketing asset.

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。

Use when the user asks for a phase-gated refactoring or redesign loop - session-blind workers map and trace the area, empirical probes precede the design, an approval gate guards implementation, and a conformance audit re-checks the branch after any design change. State persists in .episteme/DESIGN-<slug>.md. Requires the refactor agent roles registered by scripts/install-codex.sh. Keywords: refactor loop, redesign, design gate, enumerate before design, conformance audit.

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。

Measure, root-cause, fix, verify and record performance contention on a developer machine: cloud-sync daemons (iCloud Drive, OneDrive, Dropbox, Google Drive), file indexers, AI-tool MCP server fleets, and automation browsers left behind by tests and browser skills. Trigger when the machine is slow, apps freeze, browser or MCP tool calls time out, load exceeds the core count, or before and after any UI/UX/performance test run. Includes the L0–L4 optimisation scale and the test-hygiene contract.

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。

Check proposed stack, data flows, cloud choices, and delivery controls against declared enterprise policies, compliance frameworks, and security controls. Trigger at R2/R3 risk classification, before locking architecture decisions, or when the operating profile names a governance pointer.

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。

Cloud guardrails for any vendor workload — Google Cloud (GCP, Vertex AI, GKE), AWS (IAM, EKS, Bedrock), Azure (Entra ID, Policy, AKS), Alibaba Cloud (RAM, mainland/international residency). Enforces identity least-privilege, mechanical policy, data boundaries, residency, cost caps, network egress and observability, with official-source validation before any claim. Trigger on any cloud infrastructure design, review, Terraform plan, or LLM/agent deployment; the-architect routes here.

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。

LLM and cloud cost awareness — model tiering, token budgets, right-sizing, and when a cheaper model suffices. Trigger before finalising any architecture that calls LLMs, before scaling a workload, or when a cost estimate is needed.

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。

Use before committing to a heavy or irreversible plan — imagine it's 6 months later and this failed; enumerate why, score each mode, derive early-warning signals and preventive guardrails.

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。

Use when validation needs entry, business-logic, environment, and instrumentation guards so a bad value cannot reach the failure point — turns a local bug fix into a structural one.

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。

Plan modeや計画作成・プラン作成の依頼時に必ず発動し、必須セクションを漏れなく含む計画を作るためのガードレールを提供します。参考情報（URL/過去PR/ファイルパス）とユーザー発言（要約＋生ログ）を必須化し、テストがある場合はTDD前提と正常系/異常系テストケース記載を強制します。