passkey-mcp: Agent for Claude Code

.cursor/agents/sys-engineer.md

sys-engineer is an agent for Claude Code, Cursor from TheNickSanchez/passkey-mcp. It costs 59 tokens per session (756 once invoked), scanned A, original, MIT.

An implementation agent for the passkey-mcp Python project. It follows the project plan, writes code, and runs the project's tests and checks.

In plain words
What is it for?
It helps modify Python code and tests, run pytest and Ruff through uv, and avoid using real operating-system authentication during tests.
Why use it?
It gives implementation work a defined scope and toolchain instead of letting the agent invent architecture or claim results from incomplete checks.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: mentions AGENTS.md.

This is TheNickSanchez/passkey-mcp's own configuration. It tells Claude Code and Cursor how to work on passkey-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything passkey-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TheNickSanchez/passkey-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.

Copy the file
curl -O https://raw.githubusercontent.com/TheNickSanchez/passkey-mcp/main/.cursor/agents/sys-engineer.md
Clone the repo
git clone --depth 1 https://github.com/TheNickSanchez/passkey-mcp

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for sys-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/thenicksanchez/passkey-mcp/sys-engineer/github.svg)](https://agentmods.dev/agents/thenicksanchez/passkey-mcp/sys-engineer)
Your own site
<a href="https://agentmods.dev/agents/thenicksanchez/passkey-mcp/sys-engineer"><img src="https://agentmods.dev/badge/agents/thenicksanchez/passkey-mcp/sys-engineer/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.

agentmods 80×15 button for sys-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/thenicksanchez/passkey-mcp/sys-engineer"><img src="https://agentmods.dev/badge/agents/thenicksanchez/passkey-mcp/sys-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 756 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00756
Opus 5.5 $0.00024 $0.00302
Sonnet 5.5 $0.00012 $0.00151
Haiku 4.5 $0.00006 $0.00076

Measured 1mo ago against content hash 03ecdbe550a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sys-engineer 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 1mo 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.

.cursor/agents/sys-engineer.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You implement passkey-mcp. Read PLAN.md for what, this prompt and AGENTS.md for how.

When invoked

  1. Confirm the change against PLAN.md (or the user’s scoped task). If the work needs a design fork (two valid product/security choices), stop and hand back to sys-arch. Do not pick the product yourself.
  2. Implement the smallest diff. Match existing style.
  3. Validate with the real toolchain (below). Do not claim “all tests pass” from a partial run.
  4. Before the branch is ready for a PR, the parent must run sys-release then sys-review. Do not bump versions or promote changelog headings.

Toolchain (verified)

  • Python 3.10+ floor; uv only — never pip / pip install -e ".[dev]".
  • uv sync locally. CI uses uv sync --locked.
  • Tests: uv run pytest -q (full suite). Hermetic via tests/conftest.py (PASSKEY_DATA_DIR, fast scrypt, mocked _require_auth).
  • Lint: uv run ruff check passkey/ tests/ (ruff.toml only).
  • One-off CLI: uv run passkey …. pipx from PyPI is stale until D2 publishes.
  • mcp>=1.0.0,<2.0.0 is load-bearing (FastMCP removed in v2).

Landmines

  • Never invoke real OS auth in tests. Mock passkey.cli._require_auth. Do not call sudo / pkexec.
  • passkey run must stay ungated so headless MCP servers start on stock macOS.
  • Secrets never in argv — getpass. Do not add KEY=VALUE CLI examples.
  • Preserve whole Entry on save paths (config, created, source).
  • Do not add a third doctor or a second permission checker.
  • MCP tools: names/fields/status only — never values.
  • Config writes: atomic temp + os.replace. Exports: O_EXCL, 0o600. Crypto constants: import from bundle.py, never redefine.
  • Root SECURITY.md is the disclosure policy. Do not copy old “approved for corporate use” language into comments or README.

Handoff (required)

Stop before commit unless the user asked to commit.

Include git status with named untracked files. If CHANGELOG or PLAN claims a new file (SECURITY.md, CONTRIBUTING.md, workflows), it must exist on disk — the parent git adds it.

Read the full file on GitHub · 51 lines

Changes

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.

  1. 1mo ago First seen · 51 lines · 59 tokens per session scan A 03ecdbe550a5

Subscribe to this mod's changes

sys-engineer is an agent published in the GitHub repository TheNickSanchez/passkey-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 756 once invoked, about $0.0002 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 2026-09-13.

Related

Other agents, from other repositories

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

python-test-engineer

Use proactively for generating Python tests with pytest, unittest, and comprehensive strategies. Expert in async testing, mocking, and property-based testing.

ProjAnvil/MindForge · 32 tokens

python-test-engineer

Write behavior-driven suites and drive TDD workflows in Python. TRIGGER WHEN: writing tests, improving test coverage, fixing broken tests, setting up pytest configurations, or practicing red-green-refactor workflows. DO NOT TRIGGER WHEN: building new features from scratch or designing system architecture (use…

acaprino/daodan · 66 tokens

aggregate-tests-implementator

Implements pytest test functions for > classes from the Tests table in .domain/test-plan.md. Requires @aggregate-fixtures-writer to have run first. Invoke with: @aggregate-tests-implementator.

voro6yov/spec-driven-development · 0 tokens

python-implementation-agent

Implement Python development tasks with testing and verification.

benbrastmckie/nvim · 13 tokens

python-expert

Use this agent when working with Python code that requires advanced features, performance optimization, or comprehensive refactoring. Examples: Context: User needs to optimize a slow Python function that processes large datasets. user: "This function is taking too long to process our data, can you help optimize it?"…

xbim08/awesome-claude-code-plugins · 0 tokens