Reduce unnecessary Codex context and usage
Keep tasks focused and compare usage alongside completion quality rather than prompt length.
AI working habits
Scope a coding-agent task, choose relevant context, and compare efficiency without sacrificing completion quality.
This original, instruction-only skill helps with a specific repeatable decision process. It does not install tools or run background jobs.
Scope a coding-agent task, choose relevant context, and compare efficiency without sacrificing completion quality.
Read the complete skill before saving it in a project-local skill folder. Select the appropriate tool above for the documented discovery path. Keep durable project facts in the repository’s own instructions and use this skill when its described task applies.
The text is MIT licensed. Compatibility here means the documented SKILL.md format and folder location were reviewed; Pristren has not performed a live run through each coding tool. Judge the result using the workflow’s acceptance checks.
Tool setup checked against official documentation. Pristren has not executed this workflow through this tool.
Create the project-local skill directory
mkdir -p .agents/skills/focused-context-budgetCommand reference--- name: focused-context-budget description: Scope a coding-agent task, choose relevant context, and compare efficiency without sacrificing completion quality. --- # Focused coding context Use this for a coding task where excessive context or repeated work is a concrete concern. First define the accepted result and the checks that establish it. A shorter conversation is not a successful optimization if the task remains unfinished. Inspect entrypoints, symbols, configuration, and the narrow file paths that answer the current question. Prefer a targeted search to reading entire folders. Load long documents only for the section that resolves a decision. Keep durable project facts in concise instructions, and put conditional procedures in skills or focused references. Before enabling another integration, identify the data or action it supplies that the task actually needs. Prefer an already available repository command or read-only source when it answers the question. Do not remove useful tools or weaken permissions merely to reduce a token count. After a material change in task scope, write a compact handoff containing the objective, constraints, verified findings, changed files, failures, and next check. Avoid repeating full logs when a precise excerpt or artifact path is sufficient. For a comparison, record the same starting revision, task, model/settings, accepted-result checks, observed usage when available, retries, and elapsed time. Label missing measures as unavailable. Do not infer a cost or savings percentage from prompt length alone.
License and access: MIT for this Pristren-authored prompt or instruction text.
Keep tasks focused and compare usage alongside completion quality rather than prompt length.