| { | |
| "models": { | |
| "issue": { | |
| "columns": { | |
| "taskId": { | |
| "kind": "string" | |
| }, | |
| "githubNumber": { | |
| "kind": "string" | |
| }, |
| /** | |
| * ci-metrics — generic CI metric ingestion + PR regression comment. | |
| * | |
| * Ingest any numeric metric from CI (docker image sizes, test durations, flake | |
| * counts, bundle sizes, ...), persist it in swarm KV (latest snapshot + dated | |
| * history + a capped per-metric series for trend charts), and — when the run is | |
| * a PR — upsert a single sticky PR comment with a table diffing the PR against | |
| * the base branch's latest snapshot. | |
| * | |
| * Repeated calls within the same commit MERGE (one call per CI job is fine — |
| unbind C-b | |
| set-option -g prefix C-a | |
| bind-key C-a send-prefix | |
| # pi coding agent | |
| set -g extended-keys on | |
| set -g extended-keys-format csi-u | |
| # Misc configurations | |
| # Use a stable terminal type rather than inheriting $TERM at server-start time |
| #!/usr/bin/env bun | |
| // Canonical source: https://gist.github.com/tarasyarema/65949b462de1c06077411e4f59d9cf8b | |
| // Local changes should be synced to that gist. Byte-exact sync: | |
| // jq -n --rawfile content ~/.claude/statusline.ts \ | |
| // '{files:{"statusline.ts":{content:$content}}}' \ | |
| // | gh api -X PATCH /gists/65949b462de1c06077411e4f59d9cf8b --input - | |
| import { execSync } from 'child_process'; | |
| import { | |
| closeSync, |
| #!/bin/bash | |
| # Claude Code Multi-Account Switcher | |
| # Usage: ./claude-switch-multi.sh [account1|account2|account3|save-current|list|status] | |
| CLAUDE_DIR="$HOME/.claude" |
Verified Spec-Driven Development (VSDD) is a unified software engineering methodology that fuses three proven paradigms into a single AI-orchestrated pipeline:
| Latency Comparison Numbers (~2012) | |
| ---------------------------------- | |
| L1 cache reference 0.5 ns | |
| Branch mispredict 5 ns | |
| L2 cache reference 7 ns 14x L1 cache | |
| Mutex lock/unlock 25 ns | |
| Main memory reference 100 ns 20x L2 cache, 200x L1 cache | |
| Compress 1K bytes with Zippy 3,000 ns 3 us | |
| Send 1K bytes over 1 Gbps network 10,000 ns 10 us | |
| Read 4K randomly from SSD* 150,000 ns 150 us ~1GB/sec SSD |
| import React, { useState, useMemo } from 'react'; | |
| import { ComposedChart, Bar, Line, XAxis, YAxis, CartesianGrid, Tooltip, Legend, ResponsiveContainer } from 'recharts'; | |
| const data = { | |
| "organization": "desplega-ai", | |
| "period": { "months": 6, "since": "2025-07-19" }, | |
| "generatedAt": "2026-01-19T18:52:33.908Z", | |
| "repositories": [ | |
| { | |
| "name": "desplega.ai", |
| --- | |
| description: Continue work from a saved handoff file | |
| argument-hint: [handoff-file-path] | |
| allowed-tools: Glob(~/.claude/**), Read(~/.claude/**), Bash(mkdir -p ~/.claude/*), Bash(mv ~/.claude/hand-offs/*) | |
| --- | |
| ## Instructions | |
| You are continuing work from a saved handoff context. |
| --- | |
| name: context-handoff | |
| description: Use this agent when you need to preserve context before running out of context window space, when you want to checkpoint progress on a complex task, when transitioning between sessions, or when explicitly asked to save/store current progress. Examples:\n\n<example>\nContext: The assistant has been working on a complex refactoring task and notices the conversation is getting long.\nuser: "Continue refactoring the authentication module"\nassistant: "I notice we've been working on this refactoring for a while and the context is getting substantial. Let me use the context-handoff agent to save our progress before continuing."\n<commentary>\nThe assistant proactively recognizes context accumulation and uses the context-handoff agent to preserve state before it becomes a problem.\n</commentary>\n</example>\n\n<example>\nContext: User explicitly wants to save progress.\nuser: "Let's save where we are - I need to take a break"\nassistant: "I'll use the context-handoff agent to d |
