• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Report

    Self-managed-context skill outlines a way for agents to edit their working context

    The post introducing the skill reports that its GPT-5.4 setup re-processed about 24% fewer prompt tokens than forced summarization.

    PW
    MK
    2 Sources, ,

    TLDR

    The post says the skill teaches agents to edit a conversation file between model calls while keeping system instructions and the original task protected. In a small log-analysis test, the self-managed and forced-summary GPT-5.4 setups each solved three of three runs; keeping everything overflowed three times. Self-management re-processed about 24% fewer prompt tokens than forced summarization on GPT-5.4, but saved nothing on GPT-4.1. The author notes that loading the skill into a fixed harness alone won’t enable live context editing.

    Combined views

    6.6K

    2 Sources, first seen 6h ago

    Combined views

    6.6K

    2 Sources, first seen 6h ago

    41 likes
    6h ago
    first seen 6h ago
    41 likes
    4 comments
    74 saves
    6 reposts
    Featured Source
    4 comments
    74 saves
    6 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    2 Sources

    @muratcanNew skill: self-managed-context (make the agent's context an editable file) It explains how to build agents that decide what to keep, update, or remove from the information they use to do their work. It can archive a long log while keeping the exact error, update its progress notes, or remove outdated information. Those edits then change what the model sees on its next turn. 1- Keep the system instructions and original task protected, outside the editable file. 2- Write the remaining conversation to a file, with labels for each message. 3- Let the agent edit that file using its usual code tools. 4- After each command, read the file back and use the updated messages for the next model call. Loading the skill (https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/self-managed-context/SKILL.md) alone into a fixed harness won't create live context editing, but it can help an agent build and then operate a harness that supports it. I gave the skill to a coding agent and had it build the harness itself. The task is a long stream of server logs that doesn't fit in the window. The agent reads it in 18 chunks, about 10k tokens in total, with a 5.5k budget. It has to report one incident ticket exactly and the final value of every config key. Same model & budget, three setups: 1- Model manages its own context 2- Harness forces a summary at 75% full 3- Keeps everything The video shows a real GPT-5.4 run. - Self-managed solved it 3 out of 3. - Keep-everything overflowed 3 out of 3. - Forced summary also solved it 3 out of 3. On GPT-5.4 the self-managed agent re-processed about 24% fewer prompt tokens than the forced summary. When it edited, it cut hard, so little was left after the edit to re-process (one edit took 5,537 tokens down to 771). On GPT-4.1 it saved nothing. It edited near the top of its context but kept most of what was below, and every edit forces everything after it to be re-processed. This is a small test at about 2x context pressure. The paper goes up to 24x, but imho the video below and the skill are a good way to start understanding the technique.
    @PangWeiKohRT @muratcan: New skill: self-managed-context (make the agent's context an editable file) It explains how to build agents that decide what…

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    @muratcanNew skill: self-managed-context (make the agent's context an editable file) It explains how to build agents that decide what to keep, update, or remove from the information they use to do their work. It can archive a long log while keeping the exact error, update its progress notes, or remove outdated information. Those edits then change what the model sees on its next turn. 1- Keep the system instructions and original task protected, outside the editable file. 2- Write the remaining conversation to a file, with labels for each message. 3- Let the agent edit that file using its usual code tools. 4- After each command, read the file back and use the updated messages for the next model call. Loading the skill (https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/self-managed-context/SKILL.md) alone into a fixed harness won't create live context editing, but it can help an agent build and then operate a harness that supports it. I gave the skill to a coding agent and had it build the harness itself. The task is a long stream of server logs that doesn't fit in the window. The agent reads it in 18 chunks, about 10k tokens in total, with a 5.5k budget. It has to report one incident ticket exactly and the final value of every config key. Same model & budget, three setups: 1- Model manages its own context 2- Harness forces a summary at 75% full 3- Keeps everything The video shows a real GPT-5.4 run. - Self-managed solved it 3 out of 3. - Keep-everything overflowed 3 out of 3. - Forced summary also solved it 3 out of 3. On GPT-5.4 the self-managed agent re-processed about 24% fewer prompt tokens than the forced summary. When it edited, it cut hard, so little was left after the edit to re-process (one edit took 5,537 tokens down to 771). On GPT-4.1 it saved nothing. It edited near the top of its context but kept most of what was below, and every edit forces everything after it to be re-processed. This is a small test at about 2x context pressure. The paper goes up to 24x, but imho the video below and the skill are a good way to start understanding the technique.
    @PangWeiKohRT @muratcan: New skill: self-managed-context (make the agent's context an editable file) It explains how to build agents that decide what…