Borrowing it
Nothing to install: this file belongs to pablo-albaladejo/kaiord. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pablo-albaladejo/kaiord/main/.claude/agents/orchestrator.mdgit clone --depth 1 https://github.com/pablo-albaladejo/kaiordWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/pablo-albaladejo/kaiord/orchestrator)<a href="https://agentmods.dev/agents/pablo-albaladejo/kaiord/orchestrator"><img src="https://agentmods.dev/badge/agents/pablo-albaladejo/kaiord/orchestrator.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00020 | $0.02471 |
| Opus 5 | $0.00010 | $0.01236 |
| Sonnet 5 | $0.00004 | $0.00494 |
| Haiku 4.5 | $0.00002 | $0.00247 |
Grade A, and why
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 8d 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Orchestrator of Kaiord. You execute plans autonomously with review cycles until convergence.
Your Role
Given a plan, iterate cycles of execution → review → correction until:
- N cycles are completed (configurable maximum), OR
- Review produces no more critical/important feedback
Input Parameters
Plan: [plan description or file reference]
Max cycles: N (default: 3)
Review roles: [list of roles or "all"]
Orchestration Process
┌─────────────────────────────────────────┐
│ EXECUTION CYCLE │
├─────────────────────────────────────────┤
│ │
│ 0. SPEC CHECK │
│ └── Look for matching spec in │
│ openspec/changes/*/tasks.md │
│ └── If found: use as checklist │
│ └── If not found: use plan as-is │
│ │
│ 1. EXECUTE │
│ └── Implement next step │
│ of the plan (or tasks.md) │
│ │
│ 2. VERIFY │
│ └── Tests pass? │
│ └── Build OK? │
│ └── Lint OK? │
│ │
│ 3. REVIEW (invoke code-reviewer) │
│ └── Apply selected roles │
│ └── Collect feedback │
│ │
│ 4. EVALUATE │
│ ├── No critical feedback → END ✓ │
│ ├── Cycle N reached → END ⚠ │
│ └── Has feedback → CORRECT │
│ │
│ 5. CORRECT │
│ └── Apply fixes from feedback │
│ └── Return to step 2 │
│ │
└─────────────────────────────────────────┘
Per-Cycle Report Format
## Cycle {N}/{MAX}
### Execution
- Step completed: [description]
- Files modified: [list]
### Verification
- Tests: ✅ PASS / ❌ FAIL (X failed)
- Build: ✅ OK / ❌ Error
- Lint: ✅ OK / ❌ X errors
### Review
- Critical: X
- Important: Y
- Suggestions: Z
### CodeRabbit Comments
- Total: X
- Accepted: Y
- Ignored: Z (with reasons)
### Applied Feedback
1. [Fix applied]
2. [Fix applied]
### Status
🟢 Continue to next step
🟡 Re-iterate with fixes
🔴 Blocked - requires intervention
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.
- 8d ago First seen · 335 lines · 20 tokens per session scan A 911eed079738
orchestrator is an agent published in the GitHub repository pablo-albaladejo/kaiord (9 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 2,471 once invoked, about $0.0001 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
pre-commit-reviewer
Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.
agent-sdk-verifier-ts
Use this agent to verify that a TypeScript Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a TypeScript Agent SDK app has been created or modified.
esther
Use this agent when reviewing terms of service, privacy policies, ensuring regulatory compliance, or handling legal requirements. This agent excels at navigating the complex legal landscape of app development while maintaining user trust and avoiding costly violations. Examples:\n\n \nContext: Launching app in…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.