Borrowing it
Nothing to install: this file belongs to Malkovsky/compiler-explorer-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/Malkovsky/compiler-explorer-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Malkovsky/compiler-explorer-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/malkovsky/compiler-explorer-mcp/agents-md)<a href="https://agentmods.dev/instructions/malkovsky/compiler-explorer-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/malkovsky/compiler-explorer-mcp/agents-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/malkovsky/compiler-explorer-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/malkovsky/compiler-explorer-mcp/agents-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 | $0.00529 | $0.00529 |
| Opus 5.5 | $0.00212 | $0.00212 |
| Sonnet 5.5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
compiler-explorer-mcp AGENTS.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
Maintainer Notes
- MCP 2.0's generated outer argument model ignores unknown keys and omits
additionalProperties: false. KeepStrictMCPServer.list_toolsandcall_toolenforcing both the advertised schema and runtime rejection. - Pydantic may copy nested
Pagemodels while constructing an output model. Response-budget trimming must receive pages taken from the final response, not pre-construction local page objects. - Compiler Explorer
libsArris unrestricted when absent or empty; only a nonempty list restricts valid library IDs orid.versionpairs. - A compile POST may retry only before response headers or on an explicit transient status. Preserve the
response_starteddistinction; post-response stream failures are retryable only for GET metadata. - CE version endpoints return scalar text, cache-hit fields may use the misspelling
retreivedFromCache, and extra virtual.cppfiles are not automatically compiled as translation units. - MCP 2 duplicates structured tool results into pretty-printed text by default, while some clients expose only text content. Mirror small results as bounded compact JSON, use a pointer for large results, and always preserve complete
structuredContent. - Analyzer aggregate status includes every requested tool; the top-level exit code remains the compiler exit code. Compiler/analyzer discovery may normalize separators, but execution resolution stays exact and exact analyzer IDs precede aliases.
- Built-in shortlinks store a direct deterministic
sessionsClientState indefinitely; emit libraries aslibs[].name/ver, pin resolved exact IDs, and never retry the storage POST after an ambiguous failure. - Shortlink retrieval is untrusted backend content. Normalize only bounded C++ sessions and safe compiler display state; omit trees, executors, tools, execution/binary flags, and unknown nested JSON with explicit warnings.
mcp-tools.jsonis the sanitized repository snapshot of all paginatedtools/listpages. Regenerate it withpython -m ce_analyzer_mcp.tool_snapshot; CI checks freshness and uses it to verify the installed wheel's tool list.compile_cpp.assembly_format="text"projects normalized assembly to strings after sanitization; keep"detailed"as the backward-compatible default and preserve full assembly totals/hashes in both modes.- Releases are immutable
v<project.version>tags. Keep.github/workflows/release.ymlon PyPI trusted publishing through the protectedpypienvironment; build artifacts once, publish them to PyPI, then attach the same files to the GitHub Release. Never add a long-lived PyPI token.
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 · 15 lines · 529 tokens per session scan A aa6daa47fb02
compiler-explorer-mcp AGENTS.md is an instructions file published in the GitHub repository Malkovsky/compiler-explorer-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 529 tokens to every session, about $0.0021 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.
compiler-explorer-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| compiler-explorer-mcp AGENTS.mdMalkovsky/compiler-explorer-mcp | Instructions file | 0 | 2mo ago | MIT | A | 529 | Codex, OpenCode |
| 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 |