Agentic coding, written down properly.
The tools that write code with you are changing monthly. This site keeps up by reading the repos at a named commit, running the harnesses on real tasks, and writing down what happened, including the parts that did not work.
Latest
-
Prompt patterns for coding agents: plan mode, skills, saved prompts
Four prompt patterns from the Claude Code, Codex, and Gemini CLI docs, with exact commands and file formats, plus a script that writes one saved prompt three ways.
-
Coding agent security: prompt injection, MCP servers, and secrets
Prompt injection via tool results, MCP server trust, and secrets in config: what the Claude Code, Codex, and Gemini CLI docs commit to, plus an auditor to run.
-
When should you stop a coding agent? Budgets, loops, and the signs
The budget flags harnesses ship, the loop signatures that predict a failed run, what the research says about early stopping, and a transcript analyser.
-
What one coding task costs: tokens, dollars, minutes, three ways
A method for costing an agent task across an interactive session, a headless run, and a cheaper model, with a price calculator and a dataset of published numbers.
-
What is a coding-agent harness? The loop, tools, gate, and context
A coding-agent harness is the loop around the model. Here is what each part does, read from three real harnesses, with a 100-line runnable version you can inspect.
-
Coding agent time-to-green: how do you measure ten small tasks fairly?
A method and a first dataset for timing a coding agent from prompt to first passing check: ten defined tasks, a runner script, and only honestly filled columns.
-
Tests first with an agent: why must the test fail before it passes?
The red-green loop for agents: why a test that never failed proves nothing, hook-based gates, the lucky-pass numbers, and a script that enforces the order.
-
SWE-bench explained: what a resolve rate measures and what it misses
How a SWE-bench score is produced, what Verified changed, and five papers on harness effects, lucky passes, contamination, and realistic prompts, with a dataset.
Topics
Harnesses
The agent runners themselves: what each one does, its configuration, its permission model, and where it breaks.
6 article(s)
Workflows
Repeatable ways of working with an agent: specs, tests-first, review loops, context files, and the habits that survive contact with a real codebase.
6 article(s)
Repos Worth Reading
Open-source projects in the agentic-coding space, read at a specific commit, with what they get right.
4 article(s)
Tutorials
Build something end to end with an agent, including the prompts, the diffs, and the fixes.
3 article(s)
Measurements
Numbers instead of vibes: token costs, time-to-green, benchmark results, and how they were collected.
3 article(s)
About this site
One developer's field notes, with the transcripts and the diffs kept. More about how it is made.