agentleFS
Sign inStart free
levyfluxlevyflux/codex-skills/skills/durable-task-handoff/SKILL.md

durable-task-handoff

Skill1 starsChanged 3 months agoMITView on GitHub

Capture a durable, prompt-safe checkpoint for a long-running coding task, including objective, completed work, repository Git state, validation, constraints, and exact next step. Use after context compaction, at a phase boundary, before a task transfer, or when work must resume reliably later.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Do not put credentials, tokens, private prompt text, or raw command output in a handoff.

    line 12
  2. Distinctive:

    Prefer repository-relative changed-file descriptions over copied source code.

    line 15
  3. Distinctive:

    After resuming, re-check current repository state before acting.

    line 44

≈ “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

Durable Task Handoff

Preserve enough verified state for another session or maintainer to continue without reconstructing the task from chat history.

Boundaries

  • Do not put credentials, tokens, private prompt text, or raw command output in a handoff.
  • Inspect repositories read-only. A handoff never commits, pushes, merges, deploys, or changes branches.
  • Record uncertainty explicitly. Do not turn an assumption into a completed fact.
  • Prefer repository-relative changed-file descriptions over copied source code.

Capture a checkpoint

Requires Ruby 2.6 or newer and only the standard library.

ruby scripts/capture_handoff.rb \
  --objective "Finish the account recovery flow" \
  --trigger phase-boundary \
  --repository ./web \
  --repository ./api \
  --completed "API contract and targeted tests are complete" \
  --verification "api recovery tests: PASS" \
  --constraint "Do not deploy without explicit authorization" \
  --next-step "Wire the web form to the verified API contract"

The script writes an atomic JSON artifact under .codex/checkpoints/handoffs/ by default and prints its path. Use --output-dir to choose another durable location.

Required handoff content

  1. State the current objective and why the checkpoint exists.
  2. Describe completed work and unresolved decisions.
  3. Include each repository's root, branch or detached state, HEAD, upstream, and dirty-file list.
  4. Record fresh validation with exact scope and result.
  5. State authorization and safety constraints.
  6. Give one concrete next step that can be executed without rediscovery.

After resuming, re-check current repository state before acting; the artifact is a snapshot, not a lock.

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