agentleFS
Sign inStart free
dprakash2101dprakash2101/dotnet-production-agent-skills/skills/context-reset/SKILL.md

context-reset

Skill4 starsChanged 52 days agoMITView on GitHub

Reorient work when the user interrupts, replaces the objective, or redirects an in-progress coding task. Use only when the newest instruction makes prior intent or plans obsolete.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the latest explicit instruction changes the objective:

    line 8
  2. Distinctive:

    Stop pursuing the previous objective.

    line 10
  3. Distinctive:

    Check uncommitted changes before editing.

    line 13
  4. Distinctive:

    Do not repeatedly summarize the abandoned task or reload files solely because they mattered before.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Context reset

When the latest explicit instruction changes the objective:

  1. Stop pursuing the previous objective. Do not finish its TODOs or speculative fixes.
  2. Separate reusable facts from obsolete intent. Keep verified architecture, locations, constraints, and observed behavior only when relevant to the new objective.
  3. Discard the old plan, pending edits not needed by the new request, validation plan, and unrelated working set.
  4. Check uncommitted changes before editing. Preserve user changes; revert only abandoned agent-created changes when safe and identifiable.
  5. Define the minimum files and commands needed for the new direction, then proceed narrowly.

Do not repeatedly summarize the abandoned task or reload files solely because they mattered before. If the host supports context compaction, use it when stale context is large enough to impair the new task; preserve a short list of relevant verified facts first.

A status question or additional constraint does not by itself replace an active objective. Preserve the current task unless the user clearly redirects it; keep a concise handoff of decisions, modified files and remaining verification.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free