AIQB
TutorialsOrdinary

Your Agent Never Committed. Snapshot Every Turn to a Git Ref, Then Bisect

Source: DEV Community·
Claude

Summary

Twenty agent turns, zero commits, red tests. A Claude Code Stop hook snapshots each turn to refs/agent-turns/, then git bisect finds the turn that broke it.
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-d44b6f05cb224a7b69eb3896
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
7 real cases where ChatGPT and Claude got datasheet values wrong (and how to check them)
Disclosure: I build PartsPlan, the tool mentioned at the end. The cases below are real answers I...
Source: DEV Community · ChatGPT / Claude
TutorialsOrdinary
How I hand one conversation between Claude Code, Codex and four other coding agents
How Coincide, an open-source Mac app, lets a thread move between Claude Code, Codex, Cursor, Grok Build, OpenCode and Antigravity without re-explaining the task.
Source: DEV Community · Claude / Grok / Cursor
TutorialsOrdinary
Until Claude Code 2.1.309, Your ~/.zshenv Ran Outside the Sandbox Before Each Command
Claude Code 2.1.309 stopped shell startup files running outside the Bash sandbox. Why zsh and bash run them at all, and a one-line trace to see it.
Source: DEV Community · Claude
TutorialsOrdinary
Use AI Coding Agents Like a Pro: Fewer Tokens, Better Code
A practical playbook for Claude Code, Codex, Cursor and Copilot: manage context, cut token spend, and get code you can actually ship.
Source: DEV Community · Claude / Cursor
TutorialsOrdinary
I ran ripgrep, Serena, claude-context and my own tool on the same repo
There are a lot of ways to let a coding agent find code now. Plain grep, a language server behind...
Source: DEV Community · Claude
TutorialsOrdinary
Your AI Agent Trusts Everything It Reads — A Field Guide to Hijacking Claude, GPT, Gemini & Copilot
A README file in your ~/Downloads folder should not be able to expose your SSH keys. A calendar...
Source: DEV Community · GPT / Claude / Gemini
TutorialsOrdinary
Claude Code's Safety Telemetry Event Lived Six Days. Audit Your Agents With Git
Claude Code 2.1.307 added claude_code.safety_event. 2.1.312 stopped sending it. Alerts built only on vendor telemetry break quietly. Git and hooks don't.
Source: DEV Community · Claude
TutorialsOrdinary
Claude Code 2.1.316 Stops Asking Before Your Org's Managed Settings Apply
On Team and Enterprise logins, Claude Code 2.1.316 applies server-managed settings with no approval prompt. Subagents also get their own effort default.
Source: DEV Community · Claude
TutorialsOrdinary
Anthropic Automates Red-Teaming for Emergent Misalignment Research
Anthropic has published research showing how AI agents can automate parts of adversarial safety...
Source: DEV Community · Claude
TutorialsOrdinary
Binance hack, Claude Code extension backdoor, Northflank and Mistral Large 4: what each source says
The Binance theft totals from TRM and Elliptic, Cursor's notice on a modified Claude Code 2.1.313, Northflank's incident timeline and the Mistral Large 4 license clause.
Source: DEV Community · Claude / Cursor / Mistral