14 posts tagged #subagents.
Loop engineering's six building blocks are all context primitives wearing new names. The scheduling is cron. The part that decides whether the loop works is the context delivered on every iteration.
Stored session transcripts are an external memory most people throw away after 30 days. A skill that forks a cheap model to grep, expand, and re-rank them turns 'what did we decide about X' into ranked snippets — so the agent stops re-making old mistakes.
Decompose a reviewed spec into discrete tasks and drive it with a loop that spawns a fresh headless agent per task. Each unit of work gets a clean context window and a pass/fail gate instead of one agent compacting itself into confusion.
Most AGENTS.md files defend against imagined mistakes. Mine your own transcripts, count what the agent actually gets wrong, and let the failure distribution decide what to write — and in what order.
Subagents are sold as parallelism. The real win is context hygiene plus model arbitrage: delegate read-heavy investigation to cheap explorers so your expensive model only ever sees distilled findings.
Pairing an isolated subagent with the right tools and a thin slice of your conventions rebuilds the proven agent loop — read, pick a tool, act, report — without dragging dozens of tool-call logs back into your main thread.
When the window fills, agents cut corners and auto-compaction throws away the wrong things. Author a handoff file, eyeball it, and restart in a clean session you control.
The fix for slow, flaky agent evals isn't a faster suite — it's two loops. A cheap deterministic gate on every PR, and a slow judge suite headless on a schedule. One blocks regressions; the other discovers them.
Vague prompting isn't a skill gap you fix by writing longer prompts. It's a missing shared vocabulary — and the fix is a committed glossary, not a personal habit.
The codebase is the strongest steering signal you have — stronger than your prompt or your rules. So pay the exploration cost once, freeze it into a file, and feed it to every run.
You don't author a skill from a blank page. You send a subagent to research the problem once, and the research becomes the skill — a build artifact, not a document.
The highest-leverage thing you can do for your agent isn't a better prompt — it's a better interface. Deep modules are persistent context the agent reads at a glance.
Let peer agents talk freely and a query hot-potatoes between them, each disclaiming the task, while your bill climbs. Route everything through one orchestrator with explicit handoff rules and a turn cap, and the chaos becomes a system you can test.
A plugin isn't a convenience wrapper. It's how a workflow survives leaving your laptop — the difference between a personal habit and a team standard.