context-budget
Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.
Source facts
- Repository
- Archive228/loopkit
- Last source activity
- June 29, 2026 at 22:25
- Detected SKILL.md language
- English
- Stars
- 755
- Forks
- 123
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Showing SKILL.md
SKILL.md
Source instructions · Read-only preview- name
- context-budget
- description
- Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.
- when_to_use
- long session, huge file dump, agent forgetting earlier steps, accuracy dropping
# Context Budget
More context is not better. Past a threshold, accuracy falls off a cliff (context rot).
- **Don't dump whole files** — read the relevant function/section, not the 2000-line module.
- **Summarize, don't accumulate** — replace a 200K-token transcript with a 4K recap of the load-bearing facts.
- **Drop dead context** — once a sub-task is done, its detail leaves the window. Keep the decision, drop the trace.
- **State on disk, not in context** — progress goes to a file the next turn re-reads, not into an ever-growing prompt.
A bloated standing context (CLAUDE.md) taxes every single turn. Trim weekly. If the agent is confidently wrong, suspect the context before the model.
View on GitHub