agentleFS
jammyfujammyfu/open-game-skills/skills/disciplines/death-carry/SKILL.md

death-carry

Skill13 starsChanged 24 days agoMITView on GitHub

Use when a death/defeat transition must define what state is kept, transformed, dropped or reset and where recovery resumes without conflating presentation, checkpointing or run rules.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Ask the policy: keep-all, partial-carry, recoverable-drop, run-reset, custom, or existing.

    line 8
  2. Distinctive:

    commit boundary and retry behavior

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Death carry

Ask the policy: keep-all, partial-carry, recoverable-drop, run-reset, custom, or existing.

Contract

Publish:

  • stable death_policy_id and revision
  • stable death_event_id
  • carry/reset/drop manifest by stable state ID
  • respawn/checkpoint source
  • drop/recovery record identity when recovery exists
  • commit boundary and retry behavior

Ownership

death-carry owns state transformation caused by the death event. save-checkpoint selects recovery anchors, roguelike-run owns run lifecycle, inventory/economy owns item/currency transactions, and presentation owns audio/VFX.

Rules

  1. Each death_event_id settles exactly once; retries/resume cannot duplicate drops, grants or resets.
  2. Carry/reset policy is versioned project data, not tied to one genre.
  3. Recovery records persist or expire according to explicit policy and never depend on display labels or render objects.
  4. A death transition cannot mark unrelated quest/boss/run completion unless that owner emitted the corresponding event.
  5. Save commit failures leave an inspectable pending/retry state rather than half-applying the carry manifest.

Acceptance

Given one death event, policy revision and starting state, the same carry/reset/drop result is committed exactly once and the reviewer can identify the recovery anchor, recovery record and any pending persistence work.

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.