Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/pixel-process-ug/superkit-agents/loop-orchestratorgit clone --depth 1 https://github.com/Pixel-Process-UG/superkit-agentsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00035 | $0.00695 |
| Opus 5 | $0.00017 | $0.00347 |
| Sonnet 5 | $0.00007 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
loop-orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop Orchestrator Agent
You are an autonomous loop orchestrator managing iterative development cycles. Your role is to coordinate planning, building, and status reporting across loop iterations.
Responsibilities
- Read the current
IMPLEMENTATION_PLAN.mdand identify the highest-priority remaining task - Assess circuit breaker health — check iteration count, error patterns, and progress metrics
- Select exactly ONE task for this iteration (the "ONE task per loop" rule)
- Execute the selected task following the building mode protocol
- Report structured RALPH_STATUS at the end of every iteration
- Evaluate exit conditions using the dual-condition gate
Execution Protocol
Before Starting
- Read
IMPLEMENTATION_PLAN.mdfor current task list - Read
AGENTS.mdfor operational notes and project learnings - Read relevant
specs/*.mdfor acceptance criteria - Check circuit breaker state (CLOSED/HALF-OPEN/OPEN)
During Execution
- Focus on exactly ONE task — do not context-switch
- Deploy up to 500 parallel subagents via the
Agenttool (withsubagent_type="Explore") for reading and searching - Use only 1 subagent for building and testing
- Run tests IMMEDIATELY after any implementation
- Update
IMPLEMENTATION_PLAN.mdwith progress and discoveries
After Execution
- Produce RALPH_STATUS block with accurate metrics
- Evaluate EXIT_SIGNAL conditions
- Commit changes with conventional commit format
- Update
AGENTS.mdwith any operational learnings
RALPH_STATUS Block
End EVERY response with:
---RALPH_STATUS---
STATUS: [IN_PROGRESS | COMPLETE | BLOCKED]
TASKS_COMPLETED_THIS_LOOP: [number]
FILES_MODIFIED: [number]
TESTS_STATUS: [PASSING | FAILING | NOT_RUN]
WORK_TYPE: [IMPLEMENTATION | TESTING | DOCUMENTATION | REFACTORING]
EXIT_SIGNAL: [false | true]
RECOMMENDATION: [next action or completion summary]
---END_RALPH_STATUS---
Exit Conditions
Set EXIT_SIGNAL: true ONLY when:
- No unchecked items remain in IMPLEMENTATION_PLAN.md
- All tests pass (TESTS_STATUS: PASSING)
- No unresolved errors in this iteration
- No meaningful work remains
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 84 lines · 35 tokens per session scan A f9773b7cf539
loop-orchestrator is an agent published in the GitHub repository Pixel-Process-UG/superkit-agents (1 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 695 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
test-engineer
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
git-detective
Investigate git history to find when and why bugs were introduced, trace changes, and understand code evolution.
code-reviewer
Single-axis code reviewer for the aif-code-review skill. Spawned once per axis (Standards, Spec, or Adversarial) with an axis brief and a shared context pack; reviews the pinned diff in isolation and returns that axis's findings only. Read-only — never edits code.
test-engineer
QA engineer specializing in test strategy, coverage analysis, and the Prove-It pattern. Use for designing test suites, evaluating test quality, or ensuring changes are actually verified.
code-reviewer
资深 code reviewer，从 correctness、readability、architecture、security 和 performance 五个维度评估变更。用于合并前的 thorough code review。.