Results for “constrained-delegation”

Active Directory and network lateral movement assessment. Pass-the-hash, pass-the-ticket, Kerberoasting, AS-REP roasting, NTLM relay, SMB relay, WMI/WinRM/PSRemoting abuse, constrained/unconstrained delegation, RBCD, cross-trust exploitation, and pivoting. Uses impacket, netexec, enum4linux-ng, smbmap, smbclient, bloodhound-python, Responder, ntlmrelayx, mitm6, and ldap-utils. Chains from /post-exploit or /credential-audit.

Delegates a bounded repository task to an allowlisted external coding CLI through a guarded runner, with provider selection, timeout handling, and independent local review.

Orchestrate token-heavy research, coding, and testing by delegating bounded tasks to cheaper subagents while reserving Claude Fable for architecture, synthesis, and final review.

Live in-session delegation from Claude to Codex via the approval/delegation packet contract

Offload sub-tasks to other agents, specialist models, or background jobs, with guidance on choosing the right method and verifying results.

Guides agents to delegate tasks to specialized sub-agents using a decision tree and automatic triggers, with recursive spawning and integration with an agent-router MCP.

CEO式任务委派工作流程。当收到任何任务时使用此流程：不亲自执行，而是派发子代理执行、监控进度、汇报、验收。适用于需要高效并行处理多任务的场景。

Delegates a coding task to pi (dev/pi), a minimal terminal coding harness. This skill should be used when the user asks to "use pi", "run pi", "delegate to pi", "let pi handle this", "ask pi to", "have pi do", or invokes /pi:delegate. It bridges the current Claude Code context to the pi CLI, passing relevant files, git state, and the task description for execution by the pi-agent.

Manage Constraint entities — rules and limits the project must respect (budget, latency SLO, team size, compliance). Use when recording a rule, limit, or boundary that affects decisions — budget ceiling, latency SLO, regulatory requirement, team bandwidth.

Orchestrate expensive frontier models as reviewers and cheaper subagents for bounded, token-heavy work to optimize cost and quality.

Trigger: standard work, deming first, feedback loop checks, decision rights, delegation check. Scope: Engineering operating models, team governance, task feedback loops. Boundary: Excludes direct code implementation or design templates.

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessions.

Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system

Compacts the current conversation into a handoff document for another agent to pick up, referencing existing artifacts by path or URL instead of duplicating them.

Use when working with *.excalidraw or *.excalidraw.json files, user mentions diagrams/flowcharts, or requests architecture visualization - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)

Dispatching Parallel Agents

Design or revise a company's commercial policy governing discounts, approver thresholds, exception flows, and deal frameworks using data-backed matrices and linting tools.

Compress selected context to a target token budget while preserving decisions, evidence, constraints, and unresolved questions. Use when relevant material is already selected but too long; use context-optimization when selection, deduplication, and ordering are also required.

Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.

Use when a bounded textual artifact (prompt, rubric, tool description, extraction instruction) keeps underperforming and success can be measured with an evaluator, dataset, or trace set. GEPA proposes evaluator-backed candidate rewrites through a normal PR/proposal adoption gate. Do not use for vague behavior changes, governance/persona/core-memory edits, fake metrics, or problems whose first honest task is defining the evaluator or collecting data.

Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.

Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.

Least privilege is easy to state and hard to hold: grant each identity only the

Compress bloated project or global memory while preserving decisions, rationale, revisit triggers, provenance, and active user preferences. Load when memory exceeds budget, global memory is too large, session logs are repetitive, or before appending to an over-budget memory file.

Scaling Data-Constrained Language Models

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Multi-phase dialectical stress-test for HIGH-STAKES decisions only (architecture choices, irreversible product calls, strategic bets). Heavy-cost skill — do NOT use for routine questions, brainstorming, or simple tradeoffs. User must explicitly invoke or describe a decision they call "high-stakes", "irreversible", or "needs stress-testing". Triggers: "stress test this decision", "dialectic on", "challenge this thesis", "should I really".

Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.

当任务复杂或需要特定专长时，主动召唤其他 NPC 协同工作。

Selects a minimal, non-redundant set of facts, artifacts, skills, and references for a working decision when context is stale, uncertain, or over budget.

Convenes a multi-persona council of historical thinkers to deliberate on complex problems and synthesize a verdict.

Convenes four independent advisor voices to surface structured disagreement for ambiguous decisions, tradeoffs, and go/no-go calls before choosing a path.

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework