14 posts tagged #subagents.
The loop engineering parts list from June 2026, classified by one question: five blocks are context moves, one is a schedule, and the genre's signature failure is fixed by a seventh block the list never counted.
Your session transcripts hold every decision you've made with an agent, and the only free way to search them counts mentions instead of truth. Rank the survivors by date and the reversed decision stops winning.
A frozen spec substitutes for the memory a disposable agent doesn't have - but only if every task is genuinely independent. The arithmetic for when a flat-rate build loop actually holds.
Raw frequency tells you which failures are real. It still ranks them wrong. Weight each promoted category by what one instance costs, and the rule that looked #2 by count drops to last.
Route a codebase search to a subagent pinned to a cheap model and two things happen at once: the search itself costs a fifth as much, and only a hundredth of it ever reaches the window where your expensive model is about to think.
A 20-issue Sentry triage sweep run inline leaves 21,000 tokens of tool exhaust in the main thread. Dispatched to a subagent under a three-line return contract, it leaves 60. The ratio holds at every cadence.
When the window fills, auto-compaction writes a faithful summary and a handoff file writes an edited one. Both can be 200 tokens; next session they are 5,000 tokens apart, and the whole gap is one line saying what was ruled out.
A suite thorough enough to catch a real regression is too slow and noisy to gate every PR. Split the same 50 cases into a 32-case deterministic gate and an 18-case nightly judge sweep, and a team merging 8 PRs a day gets 156 minutes of blocked PR time back every week - without dropping a single case.
Your agent spends about 38 tokens working out where to make a change for every 1 token it spends making it. Then it pays that bill again on the next run. Here's the math, and the throwaway file that ends it.
Every ambiguous noun in a prompt forces the agent into a blind search over candidate files. A committed glossary turns that search into a lookup - and nets 4,410 tokens back on the very first prompt, no waiting required.
You don't author a skill from a blank page. You commission a subagent to research the reconciliation once - across a fifteen-service fleet, that one commission is worth 56,500 tokens saved.
Rounding decided across four files costs 5,500 tokens to trace, every time anyone asks. One deep module cuts that to 700 - and pays for itself by the fourth ask.
Full mesh and hub-and-spoke need exactly the same number of channels at three agents, which is why every swarm demo looks fine. Add a fourth specialist and the mesh pulls ahead for good - 45 paths against 10 by the time you reach ten.
Your best agent workflow is six files that live on one machine. Rebuilt through Slack and memory, all six arrive intact 9.6% of the time. A plugin makes the whole loop one installable, versioned unit your team pulls.