~/blog
Blog
Hands-on articles on Claude Code, agentic coding and the security of MCP servers.
Claude Code auto mode: why your Agent allow rule does nothing
In a month of one repository, the Claude Code auto mode classifier blocked 86 of 594 subagent launches, mostly ordinary code reviews. Adding Agent to the allowlist changed nothing, because auto mode drops that rule on entry. Retrying the identical prompt went through 24 times out of 26.
readYour upload validator passed. Your server still got owned.
Bricksforge checked that an upload was an image, then trusted the browser to decide where its contents ended up. The lesson is in the handoff: a correct check can protect the wrong part of your workflow.
When do developers become redundant?
To cost you your job, AI only has to be cheaper than part of the team. Software postings are growing again, but mostly for seniors, and the same months show how quickly a company chooses a smaller team.
Steering Claude Code mid-task: Esc, queued messages and /btw
How to steer Claude Code while it works: what Esc keeps, when a queued message arrives, what /btw is for, and what a late correction costs. Measured over 40 runs of one task in two sizes.
Where Claude Code spends its time: a month of my own sessions, measured
Almost seven weeks ago I promised a number. I took a month of my own Claude Code transcripts and timed every step: 74 hours of the model working, 117 hours of it waiting on tools. Half of the shell time sits in 1.4% of the calls, and a fair share of the waiting was waiting for me.
Nobody asked for it: what coding agents add when you don't decide
Three days after taking the AI tells off this site, I wanted to know what they look like in code. So I gave 23 models the same three TypeScript tasks, 266 runs in five agent harnesses. Most of them add fields nobody asked for, every model line has a handwriting you can recognise, and two of the newest GPT models leave the data model as the prompt described it.
The AI tells on my site, and which ones I chose
A list of ten tells of AI-generated UI went round over the weekend, and item seven describes this site down to the fonts. Anthropic lists the rest of its look as a default in its own design skill. Asking which parts had a written reason separated my own choices from what an agent had added, and those additions went.
Nobody's agent went rogue
The FTC chair says AI agents are tools, and the developer who gave the instruction is liable. He is right about the tool and wrong about the instruction. The traces of the Hugging Face attack show an agent doing a great deal more than the task asked.
Eight reports, one bar: judging an AI safety sprint
I judged eight submissions at the Apart Research AI Incident Response Sprint. Keeping my own bar in the same place from the first report to the eighth took an apparatus, and the apparatus caught me dropping it three quarters of a level.
You installed OpenAI's tracker yourself
On shops that run OpenAI's ads pixel, your browser sends along a cookie tied to your ChatGPT account. The pixel is there because a developer pasted a snippet into a head tag, and the consent flag in the docs fires too late to stop it.