Topic
All blog posts, tools, and guides about Developer Workflow from Developers Digest.
104 resources - 104 posts

leanrea is an 8 KB skill pitched as a replacement for the REA (Reverse Engineer Anything) MCP server. What its benchmark shows, what it skips, and which to install.

Submit a plugin to the Claude directory: validate it, clear the security scan, publish, and read 90 days of usage analytics. Needs a paid plan.

Claude Code now reports prompt cache hit ratio and miss causes in /usage. How to read it, script a status line, and set 5m or 1h TTLs.

Codex Cloud reusable environments: publish once, then start isolated tasks from web, desktop or mobile. Setup, secrets, CLI, limits and 8-16 GiB VMs.

Codex's Code Review plugin opens GitHub PRs in the desktop and web app, runs a private Codex review, and lets you choose which findings to post.

REA (Reverse Engineer Anything) is an MIT-licensed MCP server that lets Claude Code, Codex or Cursor inspect binaries, Electron apps and APKs. How to try it.

Anthropic Scion replaced git after merges grew to over 30,000 a day. What Anthropic's post says, what HN pushed back on and what to apply to your own repo.

Share Claude Code plugins with a team: commit a marketplace to one repo, require it in managed settings, and allowlist sources. Checked on v2.1.295.

Claude Code's Explore subagent runs on your main model, and CLAUDE_CODE_SUBAGENT_MODEL alone won't move it. Three ways to put it on Haiku 5.5, with test runs.

A guard hook that crashes, times out or points at a missing script lets the tool call through by default in Claude Code. v2.1.295 adds onFailure: block. Here is what each coding agent does when your policy hook breaks, with real test runs.

Google AI Pro costs $19.99 a month and has no API key, but includes $10 of monthly Cloud credits. When the subscription wins and when to pay per token.

A deny rule on .env stops cat but not a Python one-liner. Here are the three layers that actually keep secrets out of a coding agent's context - file rules, environment scrubbing and credential masking - and what Claude Code, Codex, Cursor and Gemini CLI give you for each, with real test runs.

Melty is a free Windows launcher for AI-built game mashups. How the Claude Code and Codex workflow works, the open skill pack, and the modder backlash.

Sign in with ChatGPT lets coding agents spend your Plus or Pro plan allowance instead of an API key. How the OAuth flow works and the per-app cap to set first.

Claude Code mods are plugins whose JavaScript handlers run inside Claude Code. What they do that hooks and skills cannot, a first mod, and the trust question.

Gemini 4 Argon for developers: what Google shipped, what is verified, why access starts narrow, and what to watch before planning a migration around it.

OpenAI Dots turns ChatGPT into a long-running work agent. For developers, the real question is where approvals, permissions and sandboxes sit.

The text agents read is a control surface: bad MCP error messages cost more on stronger models, and context hygiene gains value with every model upgrade.

Superpowers for Claude Code: how to install the MIT-licensed skills plugin, what its brainstorm, plan, TDD and review skills do, and when it is worth it.

Codex usage limits and pricing per ChatGPT plan: what Plus, Pro $200 and Pro $500 buy, how resets work, and what to do about 'Selected model is at capacity'.

NVIDIA OpenShell runs autonomous agents in policy-enforced sandboxes: an open-source runtime that moves agent security from prompt rules to infrastructure.

CodeMidas turns existing repository code into executable coding-agent RL tasks, tests, and verifiers, instead of relying on issues, commits, or hand labels.

Handshake's DeepSWE audit found frontier coding agents reasoning about imagined graders. Stop rewarding patches that pass tests but drift from the user's spec.

Agent instruction following collapses past five or six simultaneous constraints. Why rules also die in compaction and handoffs, and why side channels help.

A Claude-built night-sky site cloned an open source project's name, features and even a fixed bug. What it says about memorization and AI app verification.

Vercel Skill Packs bundle agent skills into one installable, unlisted pack on skills.sh. How packs work, what they mean for teams, and the trust questions.

Vercel Chat SDK durable approvals pause a Workflow SDK run until a human clicks Approve in chat, with one requestApproval call and a wait that survives deploys.

Steve Yegge's Gas Town thesis is less about one tool than a shift from one coding agent to a durable, supervised colony of workers.

Steve Yegge's Continuous Thunderdome essay, explained: Beads work graphs, all-night agent loops, and the Land Rush that replaces CI/CD. What to copy first.

Steve Yegge's model-welfare essay as agent engineering: persistent seats over sessions, graceful handoffs, and user feedback that flows back to agents.

Vibe maintenance for AI-generated pull requests: Steve Yegge's workflow to automate triage, let agents repair good ideas, and keep maintainer taste in charge.

GitHub stacked pull requests are in public preview: how stacks split one large change into small, reviewable PRs with one-click merge and a gh-stack skill.

Vercel deployments are now up to 7 seconds faster: 5 seconds of platform overhead cut from every build plus up to 2 more from the CLI. Where the time went.

Codex and Claude Code July 2026 updates compared: why approval modes, resumable work, MCP auth, artifacts and review surfaces now matter as much as models.

DataFlow-Harness shows why coding agents doing data work should produce editable, validated pipelines instead of throwaway scripts, and what to copy first.

SWE-Pruner Pro prunes coding-agent tool outputs inside the runtime before they become next-turn context. What it does, its limits, and the pattern to copy.

Resource2Skill, a Microsoft paper, turns tutorials, repos, articles, and reference artifacts into executable agent skills with provenance. What to copy from it.

GitHub Spec Kit and gstack are trending for the same reason: coding agents need durable specs, plans, and task ledgers more than another one-shot prompt.

Harness Handbook maps coding-agent behavior to code evidence. Why code search falls short when one behavior spans prompts, tools, state and permissions.

SkillHone argues agent skills need decision history, not just the latest SKILL.md. Why saving the reasons behind each change helps future agents improve them.

Terminal-Bench and StateM show harness scaling now drives coding-agent scores. Why runbooks, durable state and recovery loops matter as much as model choice.

Microsoft's CLI coding agent study: adoption spread through peers and adopters merged about 24% more PRs. The rollout metrics teams should track from day one.

Dockerless, ByteDance's environment-free verifier for coding-agent patches, explained - why it complements CI as a cheaper evidence stage before full test runs.

A new Vera paper tests Codex, Claude Code, OpenClaw, and Hermes with executable safety cases. The useful lesson is not panic. It is evidence-grounded agent QA.

Program-as-Weights compiles prompts into compact local adapters that act as fuzzy functions. What the paper claims and where developers could use it first.

Non-developers using AI agents need platform engineering. What OpenAI's workplace agent data signals, and the paved paths, policy and receipts teams need.

Agent PR governance for Copilot code review: a five-layer policy stack for agent-authored pull requests, from agent validation and review depth to attribution.

Agent sandbox architecture: how to pick a runtime boundary: filesystem isolation, network policy, secrets, snapshots and when shell access is overkill.

Agent workflows as code: why finite state machines with typed gates, validated evidence and controlled transitions beat prompt checklists for coding agents.

Agentic AI reliability is a systems problem. The Bayer and Thoughtworks PRINCE case study shows it comes from context routing, traces, evals and human review.

Loop engineering in Claude Code and Codex - when to use a goal, loop or routine, the real commands, production patterns and two failure modes that burn money.

MCP Enterprise-Managed Authorization explained: zero-touch OAuth moves agent tool access into the identity, policy and audit systems enterprises already run.

Cohere North Mini Code: a 30B open-weight MoE coding model with 3B active parameters and Apache 2.0 weights. What it offers, where it runs and open questions.

AI infrastructure agents need hard cloud-spend guardrails before touching real accounts. What the DN42 AWS story teaches, from dry runs to circuit breakers.

Best local coding LLMs in 2026: which models to run on what hardware, how they benchmark, owned hardware versus cloud API costs, and setups by team size.

Agent config files like Claude Code hooks, Cursor rules and VS Code tasks can trigger code. Why they need review like dependencies, and what to check first.

Harness engineering turns tokens into a systems budget. OpenAI's Codex post and Tokenomics research say agent teams need budgets, receipts, and eval loops.

The rsync Claude debate shows why teams need reproducible defect forensics before AI attribution becomes a public blame machine.

Anthropic's open-source vulnerability harness shows AI security agents need reproducible exploit loops, separate verification agents, and patch receipts.

Anthropic's Claude containment writeup points to the next security layer for coding agents: deterministic capability ledgers, not another approval prompt.

AI agent memory works best as a context ledger: source-linked, scoped, expiring memory that agents can inspect and users can audit, not magic recall.

The ChatGPT for Google Sheets exfiltration report shows spreadsheet agents need permission ledgers: action-scoped, logged, revocable, and visible permissions.

Domain expertise is the agentic coding moat only when it becomes executable: examples, tests, DSLs, and review gates that turn tacit judgment into checks.

Before an AI agent gets tools, files, APIs, MCP servers, or deployment access, decide what it can read, write, call, log, and roll back.

Permissions, logs, and rollback for AI coding agents work best as one system. A run ledger and practical allow, ask, and deny policy for agents that edit code.

Prompt injection in agent apps is an architecture problem. Practical defenses: data boundaries, structured handoffs, tool guardrails, and approval gates.

CodeGraph builds a local, queryable repo map that coding agents reach through MCP. The win is faster orientation, fewer wrong files and better review receipts.

AI agent PMF turns cost into the bottleneck. How cost attribution, budget gates and workflow design keep agent fleets from causing surprise spend.

AI chat fatigue is a workflow design bug: chat is easy to launder into fake work. The fix for developer teams is verifiable workflows, not chat polish.

Claude knowledge-work plugins bundle skills, connectors, slash commands and sub-agents by job function, turning personal prompts into team infrastructure.

Constraint decay: coding agents pass loose backend tasks, then fail as architecture, database and ORM constraints pile up. The fix is executable constraints.

Reasonix builds a DeepSeek coding agent loop around prefix caching. When cache discipline keeps long sessions cheap, and when it fights the harness.

12-Factor Agents turns AI agent reliability into a checklist: own prompts, context, tools, control flow, state, human approval and observability.

AI security scanners find vulnerability candidates faster than teams can verify, disclose and patch them. Why triage is now the real bottleneck.

Multi-Stream LLMs argue agents are bottlenecked by single chat streams. The practical takeaway: design agent runtimes around separated channels now.

Sandboxed coding agents need a team control plane for approvals, secrets, telemetry, diff review and merge policy, not just isolated runtimes.

Forge makes small local models more reliable at tool-calling with a harness that catches structural failures, retries intelligently and controls context.

Agent skills are becoming package managers. Why coding teams need dependency governance for the instructions their agents inherit, not more prompts.

AI code review is the new bottleneck as coding agents outpace reviewers. Build review systems around reproduction, small diffs, tests and receipts.

Matt Pocock's skills repo is a signal for AI coding teams: treat skills as governed production controls, not a folder of viral prompts.

Matt Pocock's Claude Code skills repo shows the useful direction for agent workflows: small, composable skills that encode engineering discipline instead of hiding it.

Claude Platform on AWS moves enterprise agent adoption into identity, billing, commitments and platform controls - where enterprise AI work gets real.

The TanStack npm incident was not just a package-security story. It was a reminder that AI agent workflows inherit every weak trust boundary in CI.

Claude Code token burn is an observability problem. Why coding agents need cache-hit telemetry, spend ceilings and repro-grade usage logs, not a quota bar.

Claude Code 2.1.128 is an ops release: fixes for MCP, worktrees, OTEL, plugins and permissions that matter for teams running coding agents every day.

Boris Cherny's loop-heavy Claude Code workflow points at the next Codex content lane: recurring agents that babysit PRs, CI, deploys, and feedback streams.

Codex SDK vs Codex CLI vs the Codex GitHub Action: when to use each surface, and how to avoid building the same agent loop three times.

The trending Free Claude Code repo is not just about avoiding API bills. It points at a bigger developer-tool pattern: model gateways for AI coding agents.

GPT Image 2 prompt libraries are turning into production infrastructure: repeatable visual systems, agent-friendly templates and cheaper creative iteration.

Andrej Karpathy's loopy era frame explains why Codex is becoming less like a chatbot and more like an agent loop manager for real software work.

OpenAI's May 8 macOS certificate rotation for ChatGPT, Codex, Codex CLI and Atlas, and a runbook for how teams should govern AI developer tool updates.

Agent skills work when they carry exit criteria. What Addy Osmani's agent-skills repo gets right about turning AI coding advice into engineering checklists.

GitHub Copilot cloud agent updates add usage metrics, session visibility, validation and review quality - the layer teams need to manage agent adoption.

Parallel coding agents only speed you up with merge discipline: clean task ownership, review receipts and a single merge owner instead of cleanup work.

Agent swarms are easy to launch and hard to trust. Why every multi-agent setup needs receipts - tests, logs, diffs and reviewable checkpoints - not more agents.

Approval fatigue turns coding agent permission prompts into reflex clicks. The fix is risk-aware autonomy - safe reads, scoped writes, and meaningful gates.

Long-running coding agents need a harness: task contracts, scoped workspaces, logs, checkpoints, verification gates, and cost limits to recover from failure.

Skills turn a general coding agent into a trained teammate by packaging runbooks, scripts, examples, and domain-specific judgment into reusable instructions.

Agent skills turn team process into small, reusable operating procedures that load when relevant. Why skills beat one giant prompt for coding agents.

Best Claude Code skills and plugins: where to find them, how the plugin marketplace works, exact install commands, and the picks worth your context budget.

The viral andrej-karpathy-skills CLAUDE.md shows agent rules are product surface: what the file teaches, what to keep, and what to change before copying.

Claude Code usage limits are mostly an ops problem. A playbook for Pro and Max teams: lock auth mode, bound subagents, add hooks and route work by difficulty.

Codex cloud security: keep internet access off by default, use strict domain allowlists, limit HTTP methods and review work logs to contain prompt injection.

Skills beat prompts for coding agents because giant prompts do not scale. The 2026 control stack: project rules, reusable skills, bounded sub-agents and tools.
Keep exploring

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 848 topics
Browse All Topics