All skills
simota avatar

/orbit

@35ffd55
by shingo imotasimota/agent-skills85 stars
15

Running autonomous loops for nexus-autoloop. Generates script sets from goals, designs operation contracts, audits live loops, and recovers state — runners that complete reliably.

Use this Skill: https://skilld.dev/gh/simota/agent-skills/orbit

This session only. Nothing lands on disk.

referencesignal-keywords.md

≈334 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Signal Keywords → Recipe

Canonical natural-language routing table for Orbit. Used by ## Subcommand Dispatch when the first token is not an explicit Recipe subcommand. An explicit subcommand match always wins over a keyword match.

Keywords / Artifacts Recipe (Request Mode)
plan, loop plan, plan document, design the loop, loop design doc plan (GENERATE — plan-only, document-first)
generate, new loop, create runner generate (GENERATE)
audit, check loop, loop status audit (AUDIT)
recover, state drift, fix loop; runner.log has failures recover (RECOVER)
health check, proactive, pre-failure Proactive Audit (PROACTIVE_AUDIT)
ralph, PROMPT.md, <promise>COMPLETE</promise>, cat PROMPT.md | claude ralph (GENERATE — Ralph variant)
goal.md exists and well-formed audit (AUDIT)
goal.md missing/vague, or unclear request generate (GENERATE — default) — see vague-goal-handling.md

Routing rules:

  • Subcommand match (first token equals a Recipe subcommand) wins if both a subcommand and a keyword apply.
  • If no keyword matches, fall back to the default Recipe (generate = GENERATE).
  • Applies to natural-language input without an explicit subcommand.

Source: SKILL.md on GitHub

1 alert13d5 checks · Risk SAFE
  • Gen Agent Trust Hub13d

    The orbit skill is a comprehensive framework for engineering and managing autonomous agent loops. It generates and audits shell scripts designed to execute tasks via various AI engines (Codex, Claude, Gemini). While the skill enables high-autonomy behaviors—including arbitrary command execution and bypassing tool permissions—it incorporates extensive safety controls such as budget caps, wall-clock timeouts, circuit breakers, and mandatory independent critic reviews to mitigate potential risks.

  • Socket13d

    2 alerts: gptAnomaly

  • Snyk13d

    Risk: LOW · No issues

  • Runlayer6mo

    5/11 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 35ffd55. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/orbit