Skip to content

AgentiaPT/vela-slides / .claude/skills/burst-bug-hunter

burst-bug-hunter

Verified

Time-boxed adversarial bug-hunting of a LIVE app driven by MULTI-STEP PLAYWRIGHT BURSTS against a persistent warm browser — not one LLM turn per CLI step. The app is opened ONCE; the agent submits full scripts that run to completion unattended (one structured result per burst); reset to a known initial state between scenarios; inherit the implementer's driver verbs instead of re-predicting selectors. Generic / repo-agnostic: all app specifics come from the repo's own config. Use when hunting bugs in a browser-drivable app under a hard wall-clock budget.

FileKindSize
.gitignoreother20 B
SKILL.mdskill md5.9 KB
assets/driver-server.mjsscript20.4 KB
assets/example-burst.mjsscript1.3 KB
assets/start-hunt.shexecutablescript744 B
assets/test-timeout-isolation.mjsscript18.9 KB
assets/vrunexecutablescript2.0 KB

assets/start-hunt.sh

View on GitHub
#!/usr/bin/env bash
# start-hunt.sh <workdir> <app-url> [config.json]
# Boots ONE warm driver-server (app opened once) in the background, waits until ready.
# app-url + config are repo-specific (see the repo's .hyper-sprint/ config).
set -euo pipefail
SK="$(cd "$(dirname "$0")" && pwd)"
WD="$1"; URL="$2"; CONFIG="${3:-}"
rm -rf "$WD"; mkdir -p "$WD"
nohup node "$SK/driver-server.mjs" "$URL" "$WD" "$CONFIG" > "$WD/server.log" 2>&1 &
pid=$!
for _ in $(seq 1 450); do [ -f "$WD/ready" ] && break; sleep 0.1; done
if [ -f "$WD/ready" ]; then
  boot_ms="unknown"
  [ -f "$WD/boot-ms" ] && IFS= read -r boot_ms < "$WD/boot-ms"
  echo "READY pid=$pid workdir=$WD browserBootMs=$boot_ms"
else
  echo "FAILED"
  tail -6 "$WD/server.log"
  exit 1
fi
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall