⭐ Must Read: tag/coding agents - ประเด็นร้อน

Level UI • 19 hours • in Articles • 9 min read

An MCP server is not a new API. It is a thin layer over the one you already have

Somewhere in the last year, "do we need an MCP server?" joined the list of questions that arrive in a brief before anyone has said what the thing is for. It is usually framed as MCP vs API, as though the Model Context Protocol were a newer kind of AP...

7 Reactions 7 Comments

James Dayalverified • 5 days • in Dev Stories • 6 min read

What AI Coding Loses That Git History Can't Tell You — B Donald Harris

🎥 DEV SPOTLIGHT

Featuring:

B Donald Harrisverified•Developer

AI coding agents can generate code faster than ever—but can developers still explain why that code exists? In this CoderLegion Developer Spotlight, software architect and founder B Donald Harris shares how AI-assisted development has reignited his p...

33 Reactions 5 Comments

IgorGanapolsky • Oct 5 • in Articles • 1 min read

Check the tool call before a coding agent runs it

A system prompt asks the model to behave. The tool call still goes out when the model ignores that ask. ThumbGate sits in front of the call. The PreToolUse hook reads the command before it runs and can block it. A thumbs-down on a bad call becomes a...

2 Reactions 2 Comments

Francesco Bianco (yafb) • Sep 22 • in Articles • 4 min read

Your AI Coding Agent Is Paying to Read Code It Doesn't Need

Your AI Coding Agent Is Paying to Read Code It Doesn't Need AI coding agents have become surprisingly good at changing code. But we are still giving them files as if they were human developers sitting in front of an editor. And that is expensive....

4 Reactions 1 Comments

Stephan Miller • Sep 15 • in Articles • 2 min read

Radio Means My Coding Agents Can Work On Problems Together

Radio provides a chat channel for your agents to communicate with each other. I already tried to do this with Claude Code, GitHub CoPilot, and OpenCode agents. But the methods I've used so far are very clunky: tmux, folders that agents watch for chan...

6 Reactions 2 Comments

AIAppsAPI • Aug 26 • in Articles • 3 min read

Why Your Coding Agent Edits The Wrong File

Most of us here have watched an agent confidently rewrite a function nobody asked it to touch, then spent the next twenty minutes rewording the prompt to make it stop. This is the writeup I wish I had read before doing that for the tenth time. When ...

2 Reactions 0 Comments

Tom Smithverified • 15 hours • in Articles • 9 min read

Developer Weekly Briefing — October 30, 2026

Security dominated this week, but not in the usual way. Two active campaigns turned GitHub configuration files into attack surfaces. Researchers demonstrated that the built-in browsers inside AI coding tools can read your SSH keys. And at Oracle AI ...

6 Reactions 3 Comments

Alex • Aug 24 • in Articles • 9 min read

Coding Agents Invent Facts When Denied Them. All 4 of My Probes Returned a False Zero.

A new arXiv paper watched coding agents get denied the facts they needed. They did not stop. They invented. On August 17th, a group of researchers posted a paper to arXiv with an unglamorous title and a genuinely unsettling core finding. The paper...

0 Reactions 0 Comments

yohjisakamoto • Aug 11 • in Articles • 1 min read

Cut LLM turns in MCP interactions by 75%+: a 5-to-1 example

Disclosure: I work on Tura. A typical MCP coding workflow may need five model re-entries: 1. inspect files 2. apply a patch 3. build 4. test 5. lint The commands still matter. What adds overhead is returning to the model after every step so it can...

0 Reactions 0 Comments

yohjisakamoto • Aug 8 • in Articles • 1 min read

Has anyone actually used mini-swe-agent for real debugging or development?

DeepSWE's harness comparison made me curious, so I tried mini-swe-agent myself on a matched set of debugging tasks with GPT-5.6 SOL at High reasoning. !Live Debug / Tokens benchmark screenshothttps://github.com/user-attachments/assets/6b4b8a41-cca1-...

3 Reactions 1 Comments

yohjisakamoto • Aug 4 • in Articles • 2 min read

Fewer LLM turns, more commands: a practical way to verify research-heavy agent work

!Real 15-slide deliverablehttps://github.com/user-attachments/assets/f3f269e8-b4f7-4ddf-bfff-6359c120e724 What if an agent spent less time going back to the model, but did much more useful work inside each turn? That is the idea I have been testing...

1 Reactions 0 Comments

yohjisakamoto • Aug 3 • in Articles • 1 min read

5 coding-agent turns vs 1 command_run workflow: full example

Disclosure: I maintain Turahttps://github.com/Tura-AI/tura. Here is the simple idea. A normal coding agent may use five separate LLM turns for one predictable workflow. Turn 1 — inspect rg -n "TODO|commandrun|handler" crates/ rg --files crates/run...

1 Reactions 1 Comments

yohjisakamoto • Jul 25 • in Articles • 2 min read

Why My Open-Source Project Hasn't Done Better

Disclosure: I am the maintainer of Tura. I am posting this to ask for candid advice about open-source communication and evaluation, not as an independent review of my own project. Since the beginning of 2026, projects such as RTK, Caveman, and Ponyt...

3 Reactions 1 Comments

yohjisakamoto • Jul 21 • in Articles • 1 min read

How GPT-5.6 sol token is used in Codex

Disclosure: I maintain Tura, which hosts the full test record. I ran 280+ Codex CLI sessions with GPT-5.6 Sol. In the current build, fewer commands per model turn can mean more turns and more cached-input cost. Most benchmarks favor 5.6 Sol on cost...

8 Reactions 1 Comments

Welcome to Coder Legion

Connect with 5,750 amazing developers

Don't have an account? Sign up

OR

Recent posts tagged coding-agents