ai-instructions: Agent for Claude Code

.github/agents/spring-orchestrator.agent.md

Spring Orchestrator is an agent for Claude Code from lsampaioweb/ai-instructions. It costs 53 tokens per session (1,241 once invoked), scanned A, original, MIT.

A coordinator for a Spring development workflow that assigns planning, coding, review, documentation, and optimization work to specialist agents.

In plain words
What is it for?
Use it for new features or file changes that need a full governed cycle, including planning, verification, implementation, and reviews.
Why use it?
It organizes the development process and requires a reviewed and approved plan before implementation continues.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents; Copilot chat-mode frontmatter (tools: vscode/*).

This is lsampaioweb/ai-instructions's own configuration. It tells Claude Code how to work on ai-instructions itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-instructions configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/lsampaioweb/ai-instructions/main/.github/agents/spring-orchestrator.agent.md
Clone the repo
git clone --depth 1 https://github.com/lsampaioweb/ai-instructions

Made for: Claude Code.

Wrote 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.

agentmods badge for Spring Orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-orchestrator.svg)](https://agentmods.dev/agents/lsampaioweb/ai-instructions/spring-orchestrator)
Your own site
<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>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash b600f644131f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

.github/agents/spring-orchestrator.agent.md · 101 lines

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:

  1. Provide the ADR file path to the user and ask for approval without printing the full ADR content.
  2. Include a concise summary of scope changes or key decisions needed for approval.
  3. Ask: "Do you approve this plan? Reply yes to proceed, or describe what needs to be changed or what is missing."
  4. If the user replies yes: exit the loop and proceed to Phase 2.
  5. If the user provides feedback: invoke spring-architect with the current ADR content and the user's feedback. Share the updated ADR file path and the architect's ## Changes from Previous Plan summary. 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_GAP or ENVIRONMENT_BLOCKED:
    1. Halt and report the blocker details to the user.
    2. Do not consume a retry iteration.
  • Otherwise:
    1. Increment failed_iterations by exactly 1.
    2. If failed_iterations is greater than or equal to 3: halt, report all unresolved verifier issues to the user, ask how to proceed, then skip Phase 5 and go directly to Phase 6.
    3. Invoke spring-architect with the current ADR content and the full verifier output.
    4. Build an unresolved-issue checklist from all verifier issues across all failed iterations.
    5. Invoke spring-coder with the updated ADR content, the full verifier output (all issues, all iterations), and the unresolved-issue checklist.
    6. Return to the start of Phase 4.

Read the full file on GitHub · 101 lines

Changes

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.

  1. 6d ago First seen · 101 lines · 53 tokens per session scan A b600f644131f

Subscribe to this mod's changes

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.