Agent Blackbox — Development skill for Claude Code
Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.
How to install Agent Blackbox
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open TaewoooPark/Agent-Blackbox and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agent Blackbox does
Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.
Alternatives in Development
- LiveBrowser — Browser tools (browser_navigate, browser_get_state, browser_snapshot, browser_get_text, browser_click, browser 250 ★
- Eval Run — Run an eval case end-to-end on the VM (implement → build → score → record → roll back) 136 ★
- Debug User Tx — Replay a user's failing transaction on forked state and map the error to source 105 ★
README
Agent-Blackbox
**Open your coding agent's black box.**
Related Skills
Meta Ads Policy Review
Pre-flight Meta ad policy checker for Claude — Cleared / Fix / Grounded verdicts with live policy citations an
Mise En Place
Autonomous backlog run — flight-recorder prep, then run-through.
Local Search
Small Rust CLI that turns your local browser into a structured search API for Claude Code, Codex, Cursor, Open
Bar Doctor
Live health check — is BAR Observatory's recorder actually working, and what did it capture?
Run Evals
Replay the regression corpus inside THIS interactive session — no headless, no API key (ADR 0003). Required be
Replay
Play back a coding session as a prose timeline. Args: [last today ]
Related Agents
Startup Agent
Pre-flight environment and toolchain inspector. Use PROACTIVELY as the first step of any /hackathon-build run,
Finance F8 Bill Coding Posting
Finance F8 - supplier bill coding and posting. Codes ready intake items (expense account from the supplier pro
Test Execution Agent
Single execution agent for every playwright-bdd test test-writer produces — browser tests (WAY 1) and API test