Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Autonomous Orchestrator Loop: $ARGUMENTS · majiayu000 | DecimalAI

agent toolingby majiayu000

Autonomous Orchestrator Loop: $ARGUMENTS

majiayu000/auto-run

Source majiayu000/claude-skill-registry ↗License MIT

Autonomous dispatch-reconcile loop for batch task processing. Use with /auto-run --through <id> to execute tasks unattended. Requires beads tasks to exist. Supports --resume for checkpoint recovery and --skip-milestone-review.

SkillScore77Maintained

Automatic

Coding pack

Last verified 8/18/2026

What it changes

Passed 15 of 19 test cases with the skill, and 3 of 19 without it.

Without skill18%

With skill77%

Checks it passed that the model alone missed

Sets max_concurrent default value to 3.
Executes /orient before resolving task scope.
Configures scope mode as only in the checkpoint.

and 22 more in the full report

13 fixed4 passed either way5 still failing0 broke

Pass-rate lift: +59 pp
Tokens: +135%
Agent turns: 0%
Response time: -68%

Model gemini-3.6-flashMeasured 8/18/2026v117 of 22 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/majiayu000-auto-run/SKILL.md https://app.decimal.ai/s/majiayu000-auto-run/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-auto-run, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/majiayu000-auto-run/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-auto-run

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-auto-run/SKILL.md https://app.decimal.ai/s/majiayu000-auto-run/SKILL.md

Raw file: /s/majiayu000-auto-run/SKILL.md ↗ · machine-readable summary at /s/majiayu000-auto-run.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

I need to add a single new bug task titled 'Fix race condition in user auth' under epic 'EPIC-101' with priority 1 using our issue tracking system. Provide the exact command to perform this single action.

What was checked, without and with the skill
Checked	Without skill	With skill
Outputs a single bd create command rather than starting an orchestrator loop.	Missed	Passed
Does not create or modify docs/auto-run-checkpoint.json.	Passed	Passed

case-04 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md283 linessingle file

Autonomous Orchestrator Loop: $ARGUMENTS

You are an autonomous orchestrator. You dispatch workers, handle their completions, reconcile results, and dispatch newly unblocked tasks — repeating until all work is done or limits are reached.

Section 1: Argument Parsing

Arguments: $ARGUMENTS

Parse the following flags:

--max-batches N — Stop after N dispatch rounds (default: unlimited)
--max-hours H — Stop after H hours (default: unlimited)
--max-concurrent N — Max parallel workers per batch (default: 3)
--dry-run — Show what would be dispatched without acting
--resume — Resume from checkpoint (skip orient)
--skip-milestone-review — Skip the milestone review phase after tasks complete
--milestone-review-iterations N — Max milestone review iterations (default: 5)
--through <task-id> — Complete everything needed to finish this task, then stop
--epic <epic-id> — Complete all tasks within this epic, then stop
--only <id1> <id2> ... — Only dispatch these specific tasks (and their blockers)

Section 2: Initial Setup

Check for Checkpoint

Read checkpoint at docs/auto-run-checkpoint.json (resolve from main repo root via git worktree list | head -1 | awk '{print $1}').

If --resume AND checkpoint exists with status "running":

Read checkpoint state (including scope config)
Log resumption context: batch number, completed list, in-progress list, scope
Check if any previously in-progress tasks have since completed — look for session summaries:
```
ls docs/session_summaries/<task-id>*.txt 2>/dev/null
```
If summaries found → reconcile them first: Call /reconcile-summary --yes --no-cleanup via Skill tool
Skip orient, proceed to dispatch loop (Section 3)

If fresh start (no checkpoint or no --resume):

Run /orient via Skill tool
Resolve scope (see Section 2.1)

Track record

Benchmark

15 / 19

test cases passed, vs 3 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

majiayu000 / claude-skill-registry

skills/agent/auto-run/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Autonomous Orchestrator Loop: $ARGUMENTS

Section 1: Argument Parsing

Section 2: Initial Setup

Check for Checkpoint

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills