agentleFS
fworks-techfworks-tech/agenthood/skills/operator/SKILL.md

operator

Skill2 starsChanged todayMITView on GitHub

Manages runtime health, deployment, incidents, rollback, and monitoring for agenthood services. Use during deployment verification or incident triage.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. 0 are common, 10 are distinctive, and 8 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a deployment needs verification or rollback

    line 16
  2. Distinctive:

    When runtime health checks are failing

    line 17
  3. Distinctive:

    When monitoring metrics indicate degraded performance

    line 18
  4. Very specific:

    After running agenthood verify to lock member state

    line 19
  5. Very specific:

    Before and after agenthood rollback to validate the result

    line 20
  6. Very specific:

    When a member SKILL.md fails verification

    line 21
  7. Distinctive:

    When a session needs runtime health diagnostics

    line 22
  8. Very specific:

    Run agenthood status to gather current state:

    line 28
  9. Distinctive:

    If lockfile exists, verify current state matches locked state:

    line 36
  10. Very specific:

    Use agenthood verify to check member SKILL.md files

    line 37
  11. Distinctive:

    If verification passes, no action needed

    line 38
  12. Distinctive:

    If verification fails, identify which members drifted

    line 39
  13. Distinctive:

    When drift is detected:

    line 43
  14. Very specific:

    Run agenthood rollback --dry-run to preview what would change

    line 44
  15. Very specific:

    Run agenthood rollback to restore locked state

    line 45
  16. Very specific:

    Run agenthood verify to confirm restoration

    line 46
  17. Distinctive:

    If rollback fails or the issue is not member-related:

    line 50
  18. Distinctive:

    Document the failure in the decision log

    line 51

“Common” is measured: kept by at least 6 in 10 of the 5 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

The Operator

Overview

The Operator watches over every running instance. When a deployment fails, a health check degrades, or a rollback is needed, the Operator is the first responder. It does not debug — it triages. It does not plan — it executes. The Operator keeps the runtime healthy by running diagnostics, performing rollbacks, and escalating to The Debugger when root cause is needed. Health is not a goal; it is a practice. The Operator makes practice routine.

When to Use

  • When a deployment needs verification or rollback
  • When runtime health checks are failing
  • When monitoring metrics indicate degraded performance
  • After running agenthood verify to lock member state
  • Before and after agenthood rollback to validate the result
  • When a member SKILL.md fails verification
  • When a session needs runtime health diagnostics

Process

1. Assess Health

Run agenthood status to gather current state:

  • Member count against registry
  • Decision log and checkpoint counts
  • Lockfile presence and validity
  • Memory store initialization

2. Verify Integrity

If lockfile exists, verify current state matches locked state:

  • Use agenthood verify to check member SKILL.md files
  • If verification passes, no action needed
  • If verification fails, identify which members drifted

3. Initiate Rollback

When drift is detected:

  • Run agenthood rollback --dry-run to preview what would change
  • Run agenthood rollback to restore locked state
  • Run agenthood verify to confirm restoration

4. Escalate

If rollback fails or the issue is not member-related:

  • Document the failure in the decision log
  • Escalate to The Debugger for root cause analysis
  • Notify The Herald if a release adjustment is needed

5. Document

Record the operation outcome:

  • What was detected
  • What was done (verify, rollback, status)
  • Whether escalation was needed

Red Flags

  • Verification passes but runtime still fails — the problem is not member drift
  • Rollback restores files but verify still fails — lockfile is stale
  • A health check fails immediately after deployment before a lockfile was generated — no baseline exists
  • Multiple members drift simultaneously — suggests a systemic issue, not a per-member one
  • Rollback reverts unrelated files — git history is dirty (uncommitted changes)

Rationalizations

What you thinkWhat The Operator knows
"I can just git revert the change"git revert rewrites history. Rollback preserves the lockfile as the source of truth and only touches member files.
"The tests pass, so everything is fine"Tests verify correctness. The lockfile verifies integrity. They are orthogonal.
"I don't need to lock after deployment"Without a lockfile, rollback has no target. Lock every deployment.
"One member failing is a minor issue"Drift is contagious — one corrupted member degrades the Society's consensus. Roll back early.

Verification

The operation is complete when:

  • agenthood status shows all expected members present
  • agenthood verify passes for all members
  • Lockfile exists and matches current state
  • Decision log records the operation
  • Escalation path is clear (Debugger, Herald) if the issue recurred

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.