Preflight

Get the AI coding efficiency score for the most recent task or the session-wide rolling average.

Get Git workflow efficiency metrics: merge conflicts, aborted operations, force pushes, stale branch detection, and actionable suggestions to reduce Git friction.

Get instruction/prompt drift analysis: tracks how the project's instruction file (CLAUDE.md, or the active platform's equivalent) or system prompt changes correlate with session outcomes (success rate, token usage, thrashing).

Get latency decomposition: how much time is spent in LLM API calls vs tool execution vs overhead, with p50/p95 percentiles for each component.

Get p50/p95/p99 latency percentiles for tool calls, broken down by tool type. Use to identify which tools are slowest in the current session.

Get a data-driven model recommendation ranked by historical efficiency score, cost, and task success rate across past sessions, both overall and broken down by task outcome type (bug_fix, feature, refactor, investigation, configuration, documentation, failed_attempt).

Get per-model usage statistics: request counts, token totals (input, output, thinking, cache read, cache creation), cost, and cost per million billed tokens. Identifies the most-used model, plus any PostModelSwitch events (deliberate /model changes, automatic fallbacks, or resume) recorded this session.

Returns a narrative coaching report comparing this week's personal AI coding metrics against your historical baseline. Includes highlights, regressions, streaks, and a top recommendation. Requires at least 2 weeks of session history. Returns status: "insufficient_data" with a message when history is too sparse.

Compare AI coding assistant platforms side-by-side on a given metric: efficiency, cost, task_success, tool_calls, or error_rate. Each platform bucket is tagged with visibility_level (full-hooks, self-reported, or mcp-tools-only) — platforms differ in how much built-in tool activity Preflight can observe, so a caveat is included when compared platforms span more than one level.

Get prompt cache health: hit rate, savings, and a concrete recommendation for improving cache efficiency. A high hit rate means more context is being served cheaply from cache rather than priced as fresh input.

Get quality proxy metrics: diff apply rate, test pass rate, backtrack count, self-correction count, and degradation detection over the session lifetime.

Get personalized optimization recommendations covering cost, efficiency, prompt engineering, CLAUDE.md impact, and model selection.

Get thrashing/retry detection alerts: repeated failures or highly similar inputs within a sliding window. Identifies when the agent is stuck in a loop.

Get a list of past sessions with summary metrics (efficiency, cost, tool calls, outcome).

Get current session observability metrics: tool call counts, success rates, file access stats, and duration summaries.

Get an ordered list of recent tool calls with timestamps, names, durations, and success/failure status.

Get task lifecycle metrics: completed task count, average task duration, and average tool calls per task.

Get aggregated AI coding cost and efficiency metrics for all developers in the configured team, queried via New Relic NRQL. Requires teamId to be set in config.

Get tool selection quality score: evaluates efficiency of tool usage by detecting redundant reads, repeated failures, and unused large outputs. Score 0-1 where 1 is perfect.

Get trend data for a metric over time: weekly efficiency, cost, task success rate, or tool call counts.

Conversation turn analysis — groups tool calls by AI response, shows parallelism and turn patterns.

Get a weekly summary report with per-developer breakdown, cost, efficiency, and anti-pattern counts.

Get the complete tool call trace for a task, including sequence, duration, and anti-pattern/efficiency analysis.

Check server health: version, uptime, session ID, and connection timestamp. Also reports whether telemetry event sends are succeeding. Use when the MCP connection feels stale or tools are behaving unexpectedly.

Install PreToolUse, PostToolUse, PermissionRequest, and PermissionDenied monitoring hooks into ~/.claude/settings.json. Call when nr_observe_health reports hooks_installed: false. Requires a Claude Code restart to activate monitoring.

Explicitly mark the end of the current task (a discrete unit of work between user instructions). Call this once you finish responding to a user request. This is the universal task-boundary signal — call it on any platform, but it's the *only* boundary signal on platforms other than Claude Code (which also infers boundaries from its own AskUserQuestion/TaskUpdate tool calls). Improves the accuracy of anti-pattern, efficiency-score, and cost-per-outcome metrics, which all segment activity by task.

Record user quality feedback for a task. Helps correlate efficiency metrics with perceived quality.

Report that the current AI coding session has ended. Call this at the end of a session to finalize session metrics.

Report that a new AI coding session has begun. Call this at the start of a session to initialize session metadata for observability.

Report token usage for cost tracking. Call periodically to enable accurate cost metrics. Provide the model name and token counts from the most recent API response.

Report a tool call event for observability. Use this to report non-MCP tool calls (file reads, writes, terminal commands) that your AI assistant performs. MCP tool calls are captured automatically via the proxy.

Generate the current weekly AI coding summary and POST it to the configured Slack webhook immediately.

Register a Slack webhook URL to receive weekly AI coding cost and efficiency summaries.

Remove the registered Slack webhook for weekly digests.