agentleFS
gclmgclm/super-stack/skills/harness/task-harness/SKILL.md

task-harness

Skill0 starsChanged 7 months agoMITView on GitHub

Initialize a durable task pack under harness/tasks so long-running work has stable brief, progress, decisions, evidence, and verdict artifacts.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use when the work should be anchored in harness/tasks/<task-id>/ instead of only living in chat context.

    line 8
  2. Distinctive:

    keep task scope explicit

    line 23
  3. Very specific:

    leave stable artifacts for later review / verify / qa

    line 24
  4. Distinctive:

    write the first brief and progress snapshot

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Task Harness

Use when the work should be anchored in harness/tasks/<task-id>/ instead of only living in chat context.

Read First

  • skills/harness/task-harness/references/task-artifact-contract.md
  • skills/harness/task-harness/references/progress-and-checkpoint-rules.md
  • skills/harness/task-harness/assets/task-brief.md
  • skills/harness/task-harness/assets/task-progress.md
  • skills/harness/task-harness/assets/task-decisions.md
  • skills/harness/task-harness/assets/evidence-index.json
  • skills/harness/task-harness/assets/verdict.json

Goals

  • initialize a durable task pack
  • keep task scope explicit
  • leave stable artifacts for later review / verify / qa

Process

  1. choose or create a task-id
  2. initialize harness/tasks/<task-id>/
  3. write the first brief and progress snapshot
  4. route the next step to build, review, verify, or qa

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.

Reviews can't be read right now.

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.