Borrowing it
Nothing to install: this file belongs to nima-karami/nima-career-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/nima-karami/nima-career-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/nima-karami/nima-career-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/nima-karami/nima-career-mcp/claude-md)<a href="https://agentmods.dev/instructions/nima-karami/nima-career-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nima-karami/nima-career-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/nima-karami/nima-career-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nima-karami/nima-career-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 | $0.01205 | $0.01205 |
| Opus 5.5 | $0.00482 | $0.00482 |
| Sonnet 5.5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
nima-career-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 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
A public, read-only MCP server that exposes Nima Karami's vetted, public-safe career corpus
(curated YAML) over Streamable HTTP. It powers a terminal-style portfolio chat: visitors ask
about his experience and request tailored resume drafts. Deployed on Fly.io at
https://nima-career-mcp.fly.dev/mcp.
Two non-negotiable invariants shape the design:
- Honesty by construction. Tools may only return values that exist in the corpus. The model selects/orders/tailors pre-approved material; it never authors facts, employers, dates, or metrics. Enforced in code, not just prompts.
- Public, no secrets. This repo holds server code + a public-safe corpus only. Application-tracking and private notes live in a separate private repo and must never appear here.
Commands
uv sync --all-extras --dev # install (uv is the package manager)
uv run python scripts/verify.py # the gate: format+lint+types+SAST+tests (== CI)
uv run pytest -q # all tests (includes corpus integrity)
uv run pytest tests/test_security.py -q # one file
uv run pytest tests/test_tools.py::test_list_roles_includes_seed # one test
uv run ruff check . # lint (ruff format . to autofix style)
uv run pyright # types (checks src + tests)
uv run bandit -c pyproject.toml -r src/ # SAST
uv run nima-career-mcp # stdio (local/desktop clients)
uv run nima-career-mcp --transport streamable-http # HTTP at 127.0.0.1:8080/mcp
uv run python scripts/dump_corpus.py # dump raw + grouped + sample resumes
Inspector: npx -y @modelcontextprotocol/inspector uv run nima-career-mcp (or
uv run mcp dev dev_server.py — see dev_server.py for why the shim exists). Deploy:
fly deploy. CI runs scripts/verify.py (format+lint+types+SAST+tests) plus a Semgrep job
on push/PR. A pinned pre-commit hook (ruff check+format) is available: pre-commit install.
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 · 83 lines · 1,205 tokens per session scan A 5469b87e2fc3
nima-career-mcp CLAUDE.md is an instructions file published in the GitHub repository nima-karami/nima-career-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,205 tokens to every session, about $0.0048 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.
nima-career-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nima-career-mcp CLAUDE.mdnima-karami/nima-career-mcp | Instructions file | 0 | 2mo ago | MIT | A | 1,205 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |