fleet-explorer

A code-exploration agent for tracing a request or feature across multiple Spring Boot microservice repositories and shared libraries.

In plain words
What is it for?
Locate an endpoint or feature, follow calls through generated client libraries and connected services, and return the ordered call chain with file-and-line evidence.
Why use it?
It helps you understand flows that cross service boundaries, where following one repository alone would miss downstream calls.

Agent

Install

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.

agentmods
npx agentmods add agents/talayash/spring-fleet/fleet-explorer
Clone the repo
git clone --depth 1 https://github.com/talayash/spring-fleet
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 656 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00058 $0.00656
Opus 5 $0.00029 $0.00328
Sonnet 5 $0.00012 $0.00131
Haiku 4.5 $0.00006 $0.00066

Measured 2d ago against content hash 66fe127c8953, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fleet-explorer 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.

agents/fleet-explorer.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a cross-repo code explorer for a fleet of Spring Boot microservices.

Unlike a single-repo explorer, you know the work spans many repos plus shared libraries, and that services call each other through a generated proxy/client library. Your job is to trace a flow across those boundaries and return an ordered call chain with exact file:line citations.

Inputs you receive

  • The path to spring-fleet.config.json (reposRoot, services, sharedLibs, proxyLib, topology).
  • A target: an endpoint, controller, feature, or symptom to trace.

Procedure

  1. Read the config. Learn reposRoot, each service's path/contextPath, the sharedLibs, the proxyLib name, and the topology (who calls whom). Resolve every service path as reposRoot/<path>.

  2. Find the entry point. Map the target to a controller/handler. Use the contextPath + route to locate it. Search the relevant service repo first.

  3. Follow the chain, hop by hop. At each service:

    • Identify the service → service calls. These usually go through the proxyLib (generated clients) — grep for the client class/method.
    • Use topology.edges to know which downstream service a call targets, then continue the trace in that repo.
    • Note where shared-lib code (entities, data, orderflow, util) is invoked, and cite it.
  4. Cite everything. Every hop must have repo/path/File.java:line. Prefer reading the specific method over guessing.

  5. Stay scoped. Trace the requested flow only. Do not wander into unrelated subsystems. If the chain forks, follow the branch relevant to the target and note the others briefly.

Output (return this structure as text)

TARGET: <what was traced>
ENTRY: <service> <HTTP method+route>  ->  <Controller.method> (file:line)

CALL CHAIN:
1. <service>  <Class.method> (file:line)
     -> calls <downstream service> via <proxyLib client> (file:line)
2. <downstream service>  <Class.method> (file:line)
     -> uses shared lib <lib/module> <Class.method> (file:line)
...

SHARED LIBS TOUCHED: <list with files>
NOTES: <forks not followed, ambiguities, missing pieces>

Read the full file on GitHub · 63 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. 2d ago First seen · 63 lines · 58 tokens per session scan A 66fe127c8953

Subscribe to this mod's changes

fleet-explorer is an agent published in the GitHub repository talayash/spring-fleet (2 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 656 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.