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.
npx agentmods add skills/gradusnikov/eclipse-chatgpt-plugin/eclipse-analyzenpx skills add gradusnikov/eclipse-chatgpt-plugin --skill eclipse-analyzegit clone --depth 1 https://github.com/gradusnikov/eclipse-chatgpt-pluginWrote 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/skills/gradusnikov/eclipse-chatgpt-plugin/eclipse-analyze)<a href="https://agentmods.dev/skills/gradusnikov/eclipse-chatgpt-plugin/eclipse-analyze"><img src="https://agentmods.dev/badge/skills/gradusnikov/eclipse-chatgpt-plugin/eclipse-analyze.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 | $0.00043 | $0.01461 |
| Opus 5 | $0.00022 | $0.00731 |
| Sonnet 5 | $0.00009 | $0.00292 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
eclipse-analyze 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 4d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eclipse Code Analysis
Analyze Java code using Eclipse's JDT (Java Development Tools) infrastructure. These tools provide accurate, compiler-level analysis — not text-based guessing.
Reading Code Efficiently
These tools are designed to minimize context window usage. Follow the outline-first pattern:
-
getClassOutline — Start here. Returns class declaration, field declarations, method signatures (no bodies), and inner types — all with line numbers. A 500-line class becomes ~30 lines. Provide
fullyQualifiedClassName. SetincludeFields=falseto omit fields. -
getMethodSource — After seeing the outline, read only the methods you need. Accepts comma-separated
methodNames(e.g.,"save,findById,delete"). Returns source with line numbers. SetincludeJavadoc=falseto skip doc comments. UsemethodSignatureto disambiguate overloads (e.g.,"String"matches methods with a String parameter). -
getFilteredSource — Middle ground: returns the full source but collapses methods you don't need to their signatures. Provide
methodNamesto expand specific methods; all others are shown as one-line signatures with line ranges. SetexcludeImports=true(the default) to collapse the import block. Line numbers always match the original file for accurate editing. -
getSource — Full source dump. Use only for small classes or when you need everything. Prefer the tools above to save context.
-
readProjectResource — Read any file by path. Supports
startLine/endLinefor ranges,showLineNumbers=truefor editing, andexcludeImports=trueto collapse Java import blocks.
Choosing the Right Tool
| Scenario | Tool | Why |
|---|---|---|
| Understand class structure | getClassOutline |
Signatures only, ~90% smaller |
| Read 1-3 specific methods | getMethodSource |
Surgical reads with line numbers |
| Read class but focus on 2 methods | getFilteredSource |
Full context, collapsed noise |
| Small class (<100 lines) | getSource |
Overhead not worth optimizing |
| Referenced-library class | getSource |
Uses attached source or decompiles the class |
| Diagnose which JAR/root won | explainTypeResolution |
Shows the project-specific JDT classpath decision |
| Compare a historical file | gitReadFile |
Reads a revision or staged index without checkout |
| Non-Java file or specific line range | readProjectResource |
Works with any file type |
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.
- 4d ago First seen · 80 lines · 43 tokens per session scan A b232f493e66f
eclipse-analyze is a skill published in the GitHub repository gradusnikov/eclipse-chatgpt-plugin (167 stars, last pushed 6d ago), licensed MIT. It adds 43 tokens to every session and 1,461 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
amazon aurora dsql
Deprecated compatibility redirect for Aurora DSQL guidance. Use when a request concerns DSQL, Aurora DSQL, distributed SQL, DSQL schemas, migrations, queries, authentication, performance, or application development.
investigate-issue
Investigate a GitHub issue by fetching details, analyzing the codebase, researching documentation, and presenting an actionable implementation plan with test guidance. Use when asked to investigate, analyze, triage, or plan work for a GitHub issue. Invoked with /investigate-issue or /investigate-issue (prompts for ID).
resolve-pr-comments-stack
Resolve unresolved PR review comments across an entire Graphite (gt) stack of many PRs, bottom-up, in one working directory. Use when asked to "go through this stack and resolve comments", "clean up review comments across the whole stack", or given a list/range of PR numbers that form (or partially form) a gt stack.…
split-commit-into-stack
Split one oversized commit or branch into a stack of independently reviewable Graphite (gt) PRs - deciding what genuinely separates, what is atomic and must stay whole, and proving each lower PR builds and passes without the ones above it. Use when asked to "split this PR", "this commit is too big", "break this into a…
resolve-pr-comments
Skill "resolve-pr-comments" from maximhq/bifrost, covering resolve pr comments, usage, workflow overview, step 1: detect repository and step 2: fetch unresolved comments (graphql).