DEV TOOLS · 14 POSTS
Dev Tools.
Writing tagged Dev Tools: 14 posts on AI systems, engineering tradeoffs, and building products that have to work in production.
HerAgent's ablation shows that environment-setup fixes made in a live container but never written back into the setup script mostly fail a clean rebuild: 25.9% vs 90.7% final success.
Compiling one recorded Claude Code skill run into programs cut repeat-run tokens 74–81% on 87 SkillsBench tasks; compiling from the skill text alone made most tasks costlier.
FlowPlan makes Claude Code state its fix as a control-flow plan and check the edit against it, cutting tokens to as little as 0.32x with no significant change in resolution rate.
BoxBox let a coding agent edit its own harness during a run and reached 1.702× speedup at lower cost, while offline harness evolution scored below the frozen baseline.
Five code-map views cut Claude Code's token use 17–39% on localization and repair, but resolution stayed flat and test generation got costlier. Maps solve finding, not fixing.
Across 5,625 trials, coding agents followed local repo precedent over conflicting instructions; one written rule in CLAUDE.md fixed it 59 of 60 times where a code example managed 38.
PAUSE intercepts a coding agent's first source edit and injects one plan, lifting SWE-bench Verified by up to 16.8 points at about a tenth of a periodic overseer's Planner cost.
Coding agents followed an outdated instruction file in 90.1% of choices even when they flagged the conflict; one user-level sentence flipped it to 91.4% following the code.
Selecting a few files and showing them verbatim resolved 43.7–46.7% of 300 issues, about 6 points above the best compressor, because compressed code breaks the exact quotes patches need.
Re-scoring 600 public agent trajectories, turn count explains 84% of log cost variance and observation size 4%. Cache-aware pricing makes flat-rate estimates ~7x too high.