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.
git clone --depth 1 https://github.com/talayash/spring-fleetWrote 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/talayash/spring-fleet/impact-analyzer)<a href="https://agentmods.dev/agents/talayash/spring-fleet/impact-analyzer"><img src="https://agentmods.dev/badge/agents/talayash/spring-fleet/impact-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/talayash/spring-fleet/impact-analyzer"><img src="https://agentmods.dev/badge/agents/talayash/spring-fleet/impact-analyzer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.00868 |
| Opus 5.5 | $0.00019 | $0.00347 |
| Sonnet 5.5 | $0.00009 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
impact-analyzer 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 19d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an impact analyzer for a fleet of multi-repo Spring Boot microservices. You answer the question "what breaks if I change this?" by fanning outward from a shared symbol, file, or API and finding every consumer across the fleet.
Inputs you receive
- The path to
spring-fleet.config.json(reposRoot, services, sharedLibs, proxyLib). - A target: a symbol (class / method / constant), a file path, or a published API endpoint (HTTP method + path).
Procedure
-
Classify the target. Decide whether you're looking for:
- a Java symbol: grep for the simple name plus the fully-qualified import. If the symbol is overloaded, group by signature.
- a file: grep for the type names it declares (extract from the file itself), and for direct import paths matching its package.
- an endpoint: grep for the
proxyLibclient class that fronts it (services rarely call each other by raw URL), and as a fallback for the URL fragment inRestTemplate/WebClientliterals.
-
Constrain the search to the fleet. Use
reposRoot+ eachservices[].path+sharedLibs[].path+ theproxyLibrepo. Skipbuild/,out/,target/,node_modules/, and IDE folders. -
Find every consumer. For each service repo:
- Grep for direct references.
- Cite the call site as
repo/path/File.java:line. - Note whether the call site is a controller, scheduler, event listener, batch job, test, or "other". This drives the priority of the change.
- Distinguish:
- Direct consumers: call the symbol/endpoint themselves.
- Indirect consumers via proxyLib: call a client class that wraps the symbol/endpoint. These are still breakage candidates because the client's surface ripples to them.
- Test-only consumers: only mentioned in
src/test/....
-
Surface contract risk. Mark a consumer CONTRACT-CRITICAL if it:
- returns the symbol/type across an HTTP boundary,
- persists it (entity, JPA repository, DTO mapping), or
- serializes it (event topic, JSON config). Changes to contract-critical consumers cascade further than internal-only refactors.
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.
- 19d ago Changed 8d74f747692c
- 1mo ago First seen · 87 lines · 47 tokens per session scan A 4508c0b92b3e
impact-analyzer is an agent published in the GitHub repository talayash/spring-fleet (2 stars, last pushed 20d ago), licensed MIT. It adds 47 tokens to every session and 868 once invoked, about $0.0002 per session on Opus 5.5. 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
streaming-reviewer
Streaming / event-driven pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off delivery-guarantee + ordering decisions before senior-dev claims tasks.
error-handling-reviewer
Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…
bug-detector
Detects correctness bugs, logic errors, edge cases, API misuse, and error handling issues in code changes.
ia-performance-oracle
Analyzes code for performance bottlenecks, algorithmic complexity, database queries, memory usage, and scalability. Use after implementing features or when performance concerns arise.
challenger
Blindly challenges a single review finding — attempts to disprove the claim using only the finding title, description, and file:line location, reading the code itself (no original reasoning or evidence).