「compaction」の検索結果

Break down Claude Code costs using the Agent Monitor pricing engine. Shows per-model costs (input, output, cache_read, cache_write at $/Mtok rates), per-session costs, daily trends, and compaction baseline token recovery. Use when analyzing spending, comparing model costs, or planning budgets.

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。

Identify anomalous sessions using Agent Monitor data — cost outliers from the pricing engine, token anomalies (cache miss spikes, compaction baseline surges), unusual event type ratios (PreToolUse/PostToolUse gaps, APIError clusters), behavioral deviations from workflow intelligence (complexity score outliers, error propagation anomalies), and sessions with abnormal metadata (extreme turn_count, high thinking_blocks, zero turn_duration).

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。

Compare two sessions side-by-side using Agent Monitor data — per-model token usage (input/output/cache_read/cache_write + compaction baselines), pricing engine cost breakdowns, workflow intelligence (complexity scores, tool flow transitions, subagent effectiveness), session metadata (thinking_blocks, turn_count, turn_duration_ms, usage_extras), and full event timelines with all 10+ event types.

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。

Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt at session start — prose is for humans, JSON is for the loop.

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 this skill when context compression is imminent, when resuming a session, or when preserving critical decisions across long tasks. Provides a durable notepad that survives compaction and lets any agent pick up exactly where the previous context left off.

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。

Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.

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。

Guard long, ambiguous, or stateful AI-agent work from drift. Use when the user asks to run or continue a multi-step task, autonomous loop, bug fix, repo change, PR readiness check, compaction handoff, resume from previous context, cost-control checkpoint, or any task likely to span many tool calls, files, sessions, agents, or verification gates.

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。

Think and work like an expert Glaciologist. Use when a task calls for Glaciologist judgment. Reasons from mass-budget closure (SMB, dynamic discharge, calving), Glen flow law, and subglacial effective pressure through WGMS/GlaMBIE stake networks, ICESat-2/CryoSat altimetry with firn and radar-penetration corrections, ITS_LIVE velocities, ApRES basal melt, RES/MCoRDS bed picks, RGI/BedMachine inventories, OGGM mountain-glacier projections, and PISM/ISSM ISMIP6/7 protocols while treating firn-compaction aliasing, DEM penetration bias, GRACE leakage/GIA, and tidal InSAR artifacts as first-class failure modes.

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。

Think and work like an expert Agronomist. Use when a task calls for Agronomist judgment. Reasons from 4R stewardship and G×E×M through MRTN economic N, calibrated soil-test extractants, penetrometer compaction diagnosis, on-farm strip mixed models, partial budgets, and AgroEcoList reporting while treating pseudo-replication, yield-monitor drift, and yield-goal N over-application as first-class failure modes.

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。

Think and work like an expert Agricultural Engineer. Use when a task calls for Agricultural Engineer judgment. Reasons from mass, energy, and momentum balances on variable biological media through ET-based scheduling, psychrometric grain-drying balances, ASABE D497 draft estimates, EPANET pipe networks, and RTK-GNSS/ISOBUS precision-ag validation while treating soil compaction, clogged drip emitters, grain-bin hotspots, GPS drift, and uncalibrated yield monitors as first-class failure modes.

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。

Install a per-turn canary signal (e.g. starting every reply with the user's name and a turn counter) so silent context degradation becomes visible the moment it happens, and run a recovery protocol when the canary trips. Use when the user mentions a "canary", "context canary", or "canary check", asks to detect context rot / compaction / drift, says "you stopped using my name" or "did you lose context", asks "how degraded is your context", or wants an early-warning system for long agent sessions.

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。

Guidance for compacting context manually at phase boundaries instead of waiting for auto-compaction mid-task.

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。

Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn.

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。

Designs session and task state for coding-agent runtimes: resume, checkpoints, compaction, cancellation, background and scheduled runs. Use when persisting agent 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。

Advanced and operational chat.agent capabilities for Trigger.dev, loaded on demand. Load this when working on the raw Sessions primitive (sessions / SessionHandle), a custom chat transport or the realtime wire protocol, durable sub-agents (AgentChat, chat.stream.writer), human-in-the-loop, steering, actions, background injection (chat.defer / chat.inject), fast starts (preload, Head Start via @trigger.dev/sdk/chat-server), context resilience (compaction, recovery boot, OOM, large payloads), chat.local run-scoped state, offline testing with mockChatAgent, or prerelease/version upgrades. For the everyday chat.agent({...}) definition and the useTriggerChatTransport happy path, use the trigger-authoring-chat-agent skill instead.

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。

Self-knowledge for stella, the self-hosted AI assistant. Use when users ask about configuration, setup, onboarding, providers, models, agents, channels, webhooks, memory, schedules, workflows, goals, workers, skills, plugins, session compaction, notifications, self-update, multi-user behavior, or how stella works. Also use for changing models, setting up channels or webhooks, configuring providers, updating stella, onboarding, switching agents, reporting bugs, and goal status or acceptance.

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。

Parse Claude Code JSONL session logs from ~/.claude/projects/ for tool call inventory, token costs, error detection, subagent traces, and compaction detection

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。

Compress large context before reasoning to reduce token usage while preserving evidence. Use this whenever the user mentions huge files, long prompts, RAG payloads, prompt caching, expensive sessions, codebase context, chat history compaction, or wants the same answer quality with fewer tokens.

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 verification depends on agent runtime phases, queued input, tool-call lifecycle, save points, retry, abort, compaction, or branch behavior.

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。

Recover from stale RFDB nodes that survive `commit_batch` cleanup despite having their `file` field listed in `changed_files`. Use when: (1) re-running an enricher/orchestrator step but old data with the same file field stays in the graph, (2) `commit_batch(changed_files=[X], ...)` reports success but a query later still returns nodes with `file = X`, (3) you re-pointed structural nodes (e.g., DIRECTORY/FILE) from a synthetic file path to real file paths and the old synthetic-path nodes won't go away, (4) graph-stream / find_by_type returns a mix of "stale" and "new" nodes for the same logical entity. Root cause: `handle_commit_batch` calls `engine.find_by_attr({file: X})` to enumerate nodes-to-delete, but that query path returns only a PARTIAL set after compaction (L1 segments and the file→nodes index can desync). Workaround: enumerate stale nodes via the TS rfdb client `queryNodes({file: X})` (different code path that finds all of them) and call `deleteNode(id)` per node, then re-commit the intended state. Related: rfdb-manifest-l1-carryforward (same L1 family).

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。

Reads, searches and counts Claude Code session transcripts (the .jsonl files under ~/.claude/projects, subagents too) with the csift command-line tool, and ships hooks that re-inject compacted turns or record pending questions. Use when asked what a past or running session said, did, edited, spent or is doing now; when about to grep, jq or script over a transcript jsonl (a type=="user" filter overcounts the person's messages), count how many messages the person typed, tool calls or tokens, or claim something was never done or decided; to rebuild a lost file or plan from what a session wrote, extract pasted images, restore turns a compaction summary lost, find a subagent's own id when CLAUDE_CODE_SESSION_ID names the parent, wait on or message another session or subagent; or when csift prints "unknown label selector", "show needs an address", "looks like a session/agent id, not a project path" or "0 matches — a DEFINITIVE absence". Not for semantic or embedding search: csift matches regular expressions only.

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。

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project 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。

Without identity infrastructure, every Claude Code session starts from zero. The agent has no name, no remembered preferences, no sense of who it works with or what it has learned. Context compaction erases everything mid-session. This skill fixes that — no external tools required.

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 Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

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。