Topic
Curating what information enters an LLM's context window at inference time, including retrieval, compression, memory and tool-result filtering.
Claude Code scopes rules with paths, Cursor with globs, Copilot with a comma-delimited applyTo. Copilot reads Claude's rules directory, but not the file references inside it.
Reality
The new skill exists because its author found the planning stage, not the execution stage, was the thing rationing how much work he could hand to agents overnight.
Reality
The company's CTO puts agent cost in terminal noise rather than model pricing. The 30 to 80 percent savings are vendor-reported; the 847-to-9 measurement is the part worth keeping.
Reality
The vendor says its indexed context engine cuts per-task cost 48 percent against Claude Code on the same Opus 4.8 model. The benchmark is its own, on one open-source repo.
Reality
IBM Research ran self-mined guidelines across eight models on AppWorld. One model gained 16.1 points for 5 percent more tokens; another gained nothing at all.
Reality
A dev.to writeup argues long sessions degrade structurally, not linguistically, and proposes research/plan/implement phases with a hard context clear between each.
Reality
A dev.to walkthrough argues that routing every job through one 'strongest model' helper hides the economics. The cheap fix is declaring task class and requirements before the request leaves your code.
Reality
A dev.to series argues "prompt engineering" is too narrow for agents: the package sent to the model is reassembled on every call, which makes it a runtime concern, not a file.
Reality
A dev.to comparison of OpenSpec and GitHub Spec Kit argues chat degradation is structural. The interesting part is not the diagnosis but how differently the two tools file the cure.
Reality
A dev.to write-up splits agent work into prompts, context and harness. The interesting part is the harness: tool execution, permissions, validation and recovery, all of it code you own.
Reality