All articles
28 articles, newest first. Browse by topic or subscribe to the RSS feed.
-
Agent transcripts as documentation: export, redact, link the commit
A coding-agent session log explains a diff better than the diff, but it expires, leaks secrets and changes format. A workflow and script to keep a record.
-
ccusage explained: how an agent cost dashboard prices your logs
ccusage read at commit 43af93d: where its dollar figures come from, how it removes duplicate log lines, its 5-hour blocks, and a script that re-runs the rules.
-
SWE-bench Verified task by task: 11 models, one harness, measured
The leaderboard's own per-task records for 11 models on one harness: how task size predicted failure, what a call cap keeps and saves, and what a resolve cost.
-
How often Claude Code, Codex and Gemini CLI update, measured
Q3 2026 release counts from npm timestamps for Claude Code, Codex and Gemini CLI, two release promises checked against them, and the settings that pin a version.
-
AI code review bots compared: triggers, rules files, blocking, cost
How Copilot code review, Claude Code Review and Gemini Code Assist on GitHub are triggered, what they read, whether they can block a merge, and what a review costs.
-
Flaky tests: what a green rerun tells an agent
A test failing 1% of the time needs 299 runs to reveal itself, and its rerun is green 99% of the time. The arithmetic, a dataset, and what it means for agent loops.
-
Monorepo strategies for coding agents: what loads and what runs
How Claude Code, Codex and Gemini CLI find instruction files in a monorepo, how Nx, Turborepo and pnpm scope what runs, and a script that resolves both.
-
Coding agent memory across sessions: Claude Code, Codex, Gemini CLI
What Claude Code, Codex, and Gemini CLI carry from one session to the next: transcripts, compaction, and agent-written memory, plus a script that checks what loads.
-
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: MCP prompt injection, servers, and secrets
MCP prompt injection via tool descriptions, server trust and secrets: what Claude Code, Codex and Gemini CLI docs commit to, and 593 registry packages scanned.
-
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: ten small tasks, 60 Claude Code runs
Ten small coding tasks run three times each with two Claude Code models: 60 of 60 green, medians 32.4 s and 25.6 s, tokens, estimated cost, method, limits.
-
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, what five papers found it misses, and how big a gap between two scores is real, from per-task records.
-
SWE-agent and the agent-computer interface idea, paper and repo
What SWE-agent's ACI paper argued in 2024, what the repo's tools directory looks like at commit 3ea751c0, and why its own authors now recommend a 100-line successor.
-
Spec first: how do you write a task a coding agent will finish?
A six-section spec template for coding agents, a worked CLI example, the published cost of underspecified prompts, and a linter to run before handing over.
-
Reviewing coding-agent diffs: what does the checklist catch first?
Ten patterns behind most damage in agent diffs, why a second model makes a good first reviewer, and a scanner that flags them with line references.
-
A refactor plan for a coding agent: pin the behaviour with tests first
Tests first, then structure: pin a legacy script's behaviour with characterization tests, run them against old and new code, one refactor per turn.
-
OpenHands architecture explained, read at commit f7fb0c4b
How OpenHands is built at v1.16.0. The agent step loop, workspaces and sandboxes, the condenser, the confirmation gate, and what the README now calls Agent Canvas.
-
MCP server tutorial in Python: a stdio server from scratch
What the Model Context Protocol changes for coding agents, the JSON-RPC on the wire, and a dependency-free Python stdio server exercised with a scripted client.
-
Claude Code and Codex headless: running a coding agent in CI safely
The flags for non-interactive Claude Code and Codex CLI runs, the caps that bound a job, the risks the docs name, and a CI wrapper exercised in dry-run mode.
-
Git worktrees for coding agents: one checkout per session, why?
A worktree and branch per agent task, commits after every green, deny rules for destructive git, and a helper script exercised on a real repository.
-
CLAUDE.md, AGENTS.md, and .cursor/rules: what goes in a context file
Where each coding agent looks for standing instructions, how the files load and merge, the size limits, and an audit script that finds every context file in a repo.
-
Claude Code vs Codex vs Gemini CLI: what an agent may run
The permission models of Claude Code, Codex CLI, Gemini CLI, the OpenHands SDK, and Omnigent, read from their docs on 2026-09-05, with a working settings file.
-
A one-paragraph spec for a coding agent: building a small CSV CLI
A method walkthrough for building a small CSV CLI with a coding agent: the spec, the prompts in order, the acceptance tests, and the checks that say it is done.
-
Aider explained: repo maps, edit formats, and why it still matters
Aider read at commit 5dc9490b. How the tree-sitter repo map is ranked and budgeted, what each edit format does, and a stdlib repo-map script you can run.