checkpoint-recovery
Skill1 starsChanged 51 days agoMITView on GitHub
Use when an Agent task can be interrupted, retried, resumed after restart, or needs durable progress without replaying completed model and tool calls.
In this repository21 other files it gives its agents.
- llms.txtllms.txt
- agentflow-osSkill
- api-and-interface-designSkill
- ci-cd-and-automationSkill
- context-engineeringSkill
- debugging-and-error-recoverySkill
- frontend-ui-engineeringSkill
- git-workflow-and-versioningSkill
- interview-meSkill
- makecrewSkill
- parallel-dispatchSkill
- planning-and-task-breakdownSkill
- product-deliverySkill
- review-and-critiqueSkill
- self-evolutionSkill
- shipping-and-launchSkill
- skill-auditSkill
- source-driven-developmentSkill
- task-intakeSkill
- test-driven-developmentSkill
- verification-before-completionSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 18
Stop after the retry budget or on a non-retryable failure, then report the checkpoint, failure evidence, and next action to the supervisor.
≈ “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.
Files
Checkpoint Recovery
Persist compact state at meaningful workflow boundaries and make host retries idempotent.
- Save task ID, node ID, output references, and an idempotency key after each completed boundary; never persist full chat history as a checkpoint.
- On restart, load the latest checkpoint and resume the next uncompleted node. Preserve the original task, employee, project, and file scope.
- Retry only explicitly retryable failures, with a bounded attempt count. A retry resumes from the latest checkpoint and records the reason; it does not blindly repeat completed side effects.
- Stop after the retry budget or on a non-retryable failure, then report the checkpoint, failure evidence, and next action to the supervisor.
Hosts can use JsonCheckpointStore and RetryPolicy or provide an equivalent
durable adapter with the same fields.
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
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.