agentleFS
Sign inStart free
dynos-fitdynos-fit/dynos-work/skills/resume/SKILL.md

resume

Skill2 starsChanged 8 months agoMITView on GitHub

Resume an interrupted dynos-work task from .dynos/ state. Runs only when the user explicitly types /dynos-work:resume; never auto-triggered from conversation, by session restart, by context compression, or by the word 'resume' appearing in a request.

58 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use pause, report and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • kennethleungtySkill

    pause

    Pause — stop the music (alias for /stop)

    Also in 7 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 7 projects that use this

  • MicrosoftSkill

    config

    Show or change TokenEconomizer's settings: turn micro-skills, tool pruning or the loop guard on or off, or tune them, for this repository or (with --global) every repository. Use when the user asks to configure, enable or disable TokenEconomizer or one of its mechanisms.

    Also in 3 projects that use this

  • u9401066Skill

    bug-fix

    Structured bug fixing workflow with root cause analysis and regression prevention. Triggers: BF, 修 bug, fix bug, debug, 除錯, 錯誤, error, 問題, issue, 修復, fix, 故障, fault, 異常, exception, 失敗, failure, 不能用, broken, 壞掉.

    Also in 3 projects that use this

  • GitHubSkill

    state-management

    CoreAI Sandbox's TanStack Query + mock-JSON data layer. USE WHEN: editing data-fetching hooks (`app/hooks/use*.ts`), adding mock data in `app/data/`, or wiring a component to query state.

    Also in 3 projects that use this

  • HermeticOrmusSkill

    close

    End-of-session ritual. Captures session state, updates auto-memory, writes a session summary, then exits the session cleanly.

    Also in 3 projects that use this

  • +2 more from microsoft

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 7 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not guess the next command from vibes.

    line 12
  2. Distinctive:

    If multiple active tasks exist, do not silently pick the wrong one.

    line 14
  3. Distinctive:

    If one active task: resume it automatically

    line 19
  4. Distinctive:

    If multiple active tasks: show list and ask which to resume

    line 20
  5. Very specific:

    Read manifest.json to determine current stage

    line 21
  6. Very specific:

    If manifest.json is corrupt or unreadable: report the error and suggest starting fresh with /dynos-work:start

    line 43
  7. Very specific:

    If execution-graph has segments with no evidence files: /dynos-work:execute will re-run those segments

    line 44
  8. Very specific:

    If audit-reports exist from before interruption: /dynos-work:audit will read them and determine if re-audit is needed

    line 45
  9. Distinctive:

    After a session restart during a long task

    line 49
  10. Distinctive:

    After Claude Code context was compressed mid-task

    line 50
  11. Distinctive:

    After a network interruption

    line 51
  12. Very specific:

    After manually investigating the task state with /dynos-work:status

    line 52

“Common” is measured: kept by at least 6 in 10 of the 51 edited versions of this file we could read. “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

dynos-work: Resume

Resume a dynos-work task that was interrupted.

Ruthlessness Standard

  • Do not guess the next command from vibes; derive it from the actual task stage.
  • Missing or corrupt artifacts are not "probably fine". Call them out.
  • If multiple active tasks exist, do not silently pick the wrong one.

What you do

  1. List all tasks in .dynos/ that are not DONE or FAILED (read each manifest.json). If available in this repo, use "${CODEX_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}/bin/dynos" ctl active-task.
  2. If one active task: resume it automatically
  3. If multiple active tasks: show list and ask which to resume
  4. Read manifest.json to determine current stage
  5. Tell the user which command to run next based on the stage:
StageRun this
SPEC_NORMALIZATION, SPEC_REVIEW/dynos-work:start
PLANNING, PLAN_REVIEW, PLAN_AUDIT/dynos-work:plan
PRE_EXECUTION_SNAPSHOT, EXECUTION, TEST_EXECUTION/dynos-work:execute
CHECKPOINT_AUDIT, REPAIR_PLANNING, REPAIR_EXECUTION, FINAL_AUDIT/dynos-work:audit

Output on resume

dynos-work: Resuming task-20260327-001
Title: [task title]
Current stage: CHECKPOINT_AUDIT

Run: /dynos-work:audit

Edge cases

  • If manifest.json is corrupt or unreadable: report the error and suggest starting fresh with /dynos-work:start
  • If execution-graph has segments with no evidence files: /dynos-work:execute will re-run those segments
  • If audit-reports exist from before interruption: /dynos-work:audit will read them and determine if re-audit is needed

When to use

  • After a session restart during a long task
  • After Claude Code context was compressed mid-task
  • After a network interruption
  • After manually investigating the task state with /dynos-work:status

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