Borrowing it
Nothing to install: this file belongs to soporte-defontsoft/delphi-ide-remote-mcp. 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/soporte-defontsoft/delphi-ide-remote-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/soporte-defontsoft/delphi-ide-remote-mcpWrote 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/soporte-defontsoft/delphi-ide-remote-mcp/claude-md)<a href="https://agentmods.dev/instructions/soporte-defontsoft/delphi-ide-remote-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/soporte-defontsoft/delphi-ide-remote-mcp/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/soporte-defontsoft/delphi-ide-remote-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/soporte-defontsoft/delphi-ide-remote-mcp/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 | $0.05166 | $0.05166 |
| Opus 5.5 | $0.02066 | $0.02066 |
| Sonnet 5.5 | $0.01033 | $0.01033 |
| Haiku 4.5 | $0.00517 | $0.00517 |
Grade A, and why
delphi-ide-remote-mcp 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 10d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This repository is worked THROUGH its own MCP server
Hard rule (David, 2026-09-20). When working on this repo, an agent reads,
searches, edits, configures, builds and versions through the delphi_* MCP
tools — not through the generic file/shell tools — even when it happens to be
running on the very Windows machine that hosts Delphi and the server.
Why. The only real test of this product is being used as a client. On
2026-09-20 v1.0.0-beta shipped with delphi_read (the most used tool here),
delphi_help (the first call the manual tells an agent to make) and
delphi_git status answering {"ok": true} and not one line of content to
any MCP client that understands structuredContent. The suite was green: 51
batteries, 1293 checks, 0 failures — they speak the raw protocol and read
content, so not one of them could see it. Using the server as an agent found
it in the first call.
Survey the landscape first (David, 2026-09-20)
One act, four questions - and a fifth and a sixth before any of it turns into code. You look at the landscape once - the one there is today AND the one this code will have tomorrow - and while you are there you ask the four:
1. Landscape before TOUCHING — where else does this live? You do not fix where you happen to be looking; you fix where the rule lives. If there is a single central point, patching an edge hides the bug: the symptom goes and the cause stays, now with nobody looking for it.
2. Landscape to see if it ALREADY EXISTS — is there something similar, usable or adaptable? Often the answer is a parameter on what exists, not a sibling. That reduces code and centralises the problems.
3. Landscape to COUNT - how many times is this already written? Twice is a helper with parameters: reusable, extendable, central, and a bug fixed there is fixed in every caller at once. For configuration and jail decisions, ONE reader from the very first copy: several readers of the same setting are several doors. Measured 2026-09-25: 18 hand-written copies of "the active workspace's field, else the global" - a new key with its workspace half forgotten would have fallen back to the global SILENTLY.
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.
- 10d ago Changed · +3 lines · +50 tokens per session 6ea0691063c2
- 22d ago Changed · +85 lines · +1,398 tokens per session 4ecf54f28b10
- 26d ago Changed · +3 tokens per session c10e4f8d0728
- 27d ago Changed · +31 lines · +491 tokens per session 44f030318694
- 1mo ago Changed · +22 lines · +356 tokens per session a75743431cab
- 1mo ago Changed · +2 tokens per session f29b9664dc6a
- 1mo ago Changed · +62 lines · +953 tokens per session 65972fed996b
- 1mo ago First seen · 136 lines · 1,913 tokens per session scan A cd3b5588076e
delphi-ide-remote-mcp CLAUDE.md is an instructions file published in the GitHub repository soporte-defontsoft/delphi-ide-remote-mcp (23 stars, last pushed yesterday), licensed MIT. It adds 5,166 tokens to every session, about $0.0207 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 2026-09-21.
delphi-ide-remote-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| delphi-ide-remote-mcp CLAUDE.mdsoporte-defontsoft/delphi-ide-remote-mcp | Instructions file | 23 | yesterday | MIT | A | 5,166 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |