A Two-Stage Pre-Publish Gate for User-Facing AI Text in Consumer Apps
Design a two-stage pre-publish gate for short AI-generated text you ship to end users: a deterministic rule layer plus a Claude classifier, with fail-closed handling, generation-time vetting, and a cost model. Full implementation code included.
Full-Size or Downscaled? A Per-Image Resolution Rule for Opus 4.7's High-Resolution Vision
Opus 4.7 finally read the fine texture in my wallpapers, so I sent everything at full size. My weekly image tokens jumped 2.4x. Here is the preflight that decides resolution and model per image, with the measured savings.
When You Give an API Key an Expiration Date, Expiry Becomes a Plan Instead of an Accident
The Console now lets you set expiration dates on API keys. Here is how to fold planned expiry into unattended operations — with overlapping dual keys and a local expiry ledger — so your nightly jobs never go dark.
Don't Trust the Confidence Score: Per-Class Calibration and Abstain Routing for Vision Classification
Overall accuracy looked fine while individual categories quietly collapsed. Here is how I calibrated Claude Vision's self-reported confidence per class and routed abstentions to a human queue.
Four sites, one Claude bill: attributing spend per workspace to decide which pipeline to trim
When several projects share one Claude organization, the bill arrives as a single number that hides which pipeline is expensive. Field notes on splitting that spend per workspace with the Cost and Usage Report group_by, defensively parsing the results, and deciding what to trim by cost-effectiveness.
I Could Detect Failures — Then the Alerts Grew So Loud I Stopped Noticing
The moment I could detect silent job failures, my phone started buzzing too often to be useful. Here is how I collapsed alerts by action rather than event, added hysteresis and quiet hours, and built a three-step escalation so only the pages worth waking me survive.
When Your Cowork × GitHub MCP Triage Quietly Drifts Each Run — Field Notes on Idempotency and Label Boundaries
Cowork + GitHub MCP issue triage looks perfect on the first run, then quietly breaks when left unattended: duplicate comments, reclassification churn, rate exhaustion. Field notes on idempotent prompts, label-boundary self-audits, and request budgets that keep weekly triage stable.
Handing Claude Design Mockups Straight to Claude Code: Folding the Design-to-Code Loop
The June 17 Claude Design update added codebase-aware generation. Here's how to make your tokens the single source of truth, hand mockups to Claude Code, and collapse the design-to-code round trip — with code you can copy.
An Article My Gate Rejected Got Published — The Cost of Chaining the Quality Gate and git push in One Call
In an unattended publishing pipeline, an article my quality gate had rejected went live anyway. The cause was chaining the gate and git push into a single shell call. Here is how the exit code gets swallowed, and a two-phase publish-marker design that refuses to push until every gate has demonstrably passed.
When an Announced Billing Change Is Withdrawn at the Last Minute, Change No Code
A billing change that was supposed to take effect was withdrawn on the day. To survive announce, apply, and revert without touching code, I keep platform behavior behind a single flag and project the monthly delta from real logs.
Measuring a Week of Headless Usage the Night Before the Billing Change
With headless Claude Code moving to monthly credits on June 15, I spent a week logging how many tokens my unattended runs actually consume, so I could pick a plan based on numbers instead of a guess.
What the June 15 Claude Code Billing Change Means for Headless Runs
From June 15, 2026, the Agent SDK, headless claude -p, GitHub Actions, and third-party agents move to monthly credits. Here's how a solo developer running automation decided what to keep and what to cut.