Borrowing it
Nothing to install: this file belongs to vcth4nh/idesense. 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/vcth4nh/idesense/main/CLAUDE.mdgit clone --depth 1 https://github.com/vcth4nh/idesenseWrote 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/instructions/vcth4nh/idesense/claude-md)<a href="https://agentmods.dev/instructions/vcth4nh/idesense/claude-md"><img src="https://agentmods.dev/badge/instructions/vcth4nh/idesense/claude-md/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/instructions/vcth4nh/idesense/claude-md"><img src="https://agentmods.dev/badge/instructions/vcth4nh/idesense/claude-md.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 | $0.00431 | $0.00431 |
| Opus 5.5 | $0.00172 | $0.00172 |
| Sonnet 5.5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
idesense CLAUDE.md 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 2mo 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.
What it actually says
IdeSense
An IntelliJ Platform plugin that exposes an MCP server giving coding agents the IDE's code-analysis engines — indexing, navigation, cross-references, diagnostics — with no human-in-the-IDE interaction required. The IDE is not used to edit, build, or run code on the agent's behalf; a minimal set of index-backed refactorings (rename, move file) is retained. Works across JetBrains IDEs (IntelliJ IDEA, PyCharm, WebStorm, GoLand, PhpStorm, RubyMine, CLion, RustRover, DataGrip, Android Studio).
Agent rules
- Mimic the IDE → Escalate. Every tool should return what the IDE's own action/tool window shows for the same input; faithfully mirroring the IDE is the default. When correctness can only be judged against the running IDE, or when mirroring the IDE would withhold info that's genuinely more useful to the agent, stop and ask the user — don't decide silently. Full design principle + escalation rules: ARCHITECTURE.md.
- Never run platform tests yourself (
*TestextendingBasePlatformTestCase) — CI runs them. Unit tests (*UnitTest) are fine. - Dev versioning gotcha: during iteration use a monotonic
-dev.NNsuffix onpluginVersion; IntelliJ treats an equal version string as a no-op install, so reusing a version silently keeps old code.-dev.NNnever lands onmain. Details: CONTRIBUTING.md.
Where things live
- Using the tools (agents): src/main/resources/skill/idesense/SKILL.md
- User tool reference: docs/USAGE.md
- Contributing (build/test/PR/dev-loop): docs/CONTRIBUTING.md
- Architecture & design: docs/ARCHITECTURE.md
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.
- 2mo ago First seen · 28 lines · 431 tokens per session scan A c49f480c2f16
idesense CLAUDE.md is an instructions file published in the GitHub repository vcth4nh/idesense (2 stars, last pushed 4d ago), licensed MIT. It adds 431 tokens to every session, about $0.0017 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.
idesense CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| idesense CLAUDE.mdvcth4nh/idesense | Instructions file | 2 | 4d ago | MIT | A | 431 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |