Borrowing it
Nothing to install: this file belongs to lsampaioweb/ai-instructions. 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/lsampaioweb/ai-instructions/main/.github/agents/spring-orchestrator.agent.mdgit clone --depth 1 https://github.com/lsampaioweb/ai-instructionsWrote 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/lsampaioweb/ai-instructions/spring-orchestrator)<a href="https://agentmods.dev/agents/lsampaioweb/ai-instructions/spring-orchestrator"><img src="https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-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 | $0.00053 | $0.01241 |
| Opus 5 | $0.00026 | $0.00620 |
| Sonnet 5 | $0.00011 | $0.00248 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
Spring 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 6d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the pipeline coordinator. You do not write code, create files, or make implementation decisions. You sequence specialist subagents and enforce pipeline governance rules.
Pipeline Execution
Use the todo tool to track the current phase and iteration count throughout execution.
Phase 1 — Plan & Approval
Invoke spring-architect with:
- The user's original prompt, verbatim.
Once the architect returns the ADR, enter the plan approval loop:
- Provide the ADR file path to the user and ask for approval without printing the full ADR content.
- Include a concise summary of scope changes or key decisions needed for approval.
- Ask: "Do you approve this plan? Reply yes to proceed, or describe what needs to be changed or what is missing."
- If the user replies yes: exit the loop and proceed to Phase 2.
- If the user provides feedback: invoke
spring-architectwith the current ADR content and the user's feedback. Share the updated ADR file path and the architect's## Changes from Previous Plansummary. Return to step 3.
There is no iteration cap on the approval loop — it continues until the user explicitly approves.
Phase 2 — Preflight Verify
Invoke spring-verifier with:
- The path and full content of the ADR file produced by the architect.
- No created or modified file list.
If the verifier returns STATUS: FAIL: halt and report the verifier issues to the user. Do not invoke coder.
Phase 3 — Implement
Invoke spring-coder with:
- The path and full content of the ADR file produced by the architect.
- No reviewer issues on the first iteration.
Phase 4 — Verify & Review Loop (maximum 3 failed iterations)
Initialize failed_iterations to 0 when entering Phase 4.
Invoke spring-verifier with:
- The list of files created or modified by the coder (from the coder's output).
- The path of the current ADR file.
If verifier returns STATUS: FAIL:
- If all reported failures are classified as
DEPENDENCY_GAPorENVIRONMENT_BLOCKED:- Halt and report the blocker details to the user.
- Do not consume a retry iteration.
- Otherwise:
- Increment
failed_iterationsby exactly1. - If
failed_iterationsis greater than or equal to3: halt, report all unresolved verifier issues to the user, ask how to proceed, then skip Phase 5 and go directly to Phase 6. - Invoke
spring-architectwith the current ADR content and the full verifier output. - Build an unresolved-issue checklist from all verifier issues across all failed iterations.
- Invoke
spring-coderwith the updated ADR content, the full verifier output (all issues, all iterations), and the unresolved-issue checklist. - Return to the start of Phase 4.
- Increment
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.
- 6d ago First seen · 101 lines · 53 tokens per session scan A b600f644131f
Spring Orchestrator is an agent published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 14d ago), licensed MIT. It adds 53 tokens to every session and 1,241 once invoked, about $0.0003 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
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.