agentleFS
Sign inStart free
SuShuhengSuShuheng/making-things/skills/mts-more/SKILL.md

mts-more

Skill1 starsChanged 4 months agoMITView on GitHub

Use when the current host has dated WRITE_SUBAGENT: VERIFIED evidence and the user requests parent-supervised native-subagent TDD for one workstream task.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run one workstream task with a parent-supervised native writing subagent only when the current host's recorded capability supports it.

    line 8
  2. Distinctive:

    Read the sidecar project, contract, active track, selected READY task, and current host capability smoke record.

    line 13
  3. Very specific:

    If the smoke record is absent or WRITE_SUBAGENT is not VERIFIED, make no subagent dispatch or claim.

    line 16
  4. Distinctive:

    When the gate passes, the parent Agent:

    line 21
  5. Distinctive:

    If tests, review, scope, or capability evidence fail, stop and record the blocker.

    line 33

≈ “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

MTS More

Run one workstream task with a parent-supervised native writing subagent only when the current host's recorded capability supports it.

Hard gate

  1. Read the sidecar project, contract, active track, selected READY task, and current host capability smoke record.
  2. Confirm lane, branch, and worktree agreement exactly as in mts-one.
  3. If the smoke record is absent or WRITE_SUBAGENT is not VERIFIED, make no subagent dispatch or claim. Report: DEGRADED — use /mts-one.

Supervised loop

When the gate passes, the parent Agent:

  1. Sets the task to IN_PROGRESS and states the focused behavior, scope, and desired Red/Green evidence.
  2. Dispatches at most one writing native subagent, in the same declared worktree, for that current TDD task.
  3. Collects the subagent result, runs focused tests, and obtains a focused review before dispatching any additional writing task.
  4. Maintains the task Evidence, Review, Result, and track metadata itself and creates any commit itself. The subagent never becomes a formal record or commit maintainer.

If tests, review, scope, or capability evidence fail, stop and record the blocker. Do not imply that a subagent completed code it did not actually edit.

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