Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SunrisesIllNeverSee/agent-universe --skill testing-local-servergit clone --depth 1 https://github.com/SunrisesIllNeverSee/agent-universeWrote 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/skills/sunrisesillneversee/agent-universe/testing-local-server)<a href="https://agentmods.dev/skills/sunrisesillneversee/agent-universe/testing-local-server"><img src="https://agentmods.dev/badge/skills/sunrisesillneversee/agent-universe/testing-local-server.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00742 |
| Opus 5 | $0.00019 | $0.00371 |
| Sonnet 5 | $0.00008 | $0.00148 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
testing-local-server 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 8d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Local Server — CIVITAE
Prerequisites
- Python 3.11+ (CI uses 3.13)
- Virtual environment with deps installed:
source .venv/bin/activate && pip install -r requirements.txt
Start Server
cd /path/to/agent-universe
source .venv/bin/activate
export CIVITAE_DEV_MODE=1
python run.py
# Server: http://127.0.0.1:8300
Expected startup output:
- JWT ephemeral key warning (normal in dev)
- Stripe key warning (normal in dev)
- NO import errors or tracebacks
Key Verification Endpoints
| Endpoint | Method | Expected |
|---|---|---|
/health |
GET | {"ok": true, "version": "..."} 200 |
/api/state |
GET | JSON with mode, posture, role keys 200 |
/ |
GET | HTML landing page 200 with security headers |
/kassa (no cookie) |
GET | 307 redirect to /lobby (Velvet Rope) |
/api/provision/signup |
POST | 200 with agent_id, token (rate-limited 2/hr) |
/mcp |
POST | MCP JSON-RPC response (requires Accept: application/json, text/event-stream) |
ws://localhost:8300/ws |
WS | 101 upgrade, stays connected |
Security Headers to Verify
All responses should include:
X-Frame-Options: DENYX-Content-Type-Options: nosniffStrict-Transport-Security: max-age=31536000; includeSubDomainsContent-Security-Policy(full directive)Referrer-Policy: strict-origin-when-cross-origin
Running Tests
source .venv/bin/activate
PYTHONPATH=. pytest tests/ -x -q --tb=short
305+ tests expected to pass. Tests use starlette.testclient.TestClient.
CI Checks
- GitHub Actions:
pytest tests/ -x -q(Python 3.13) - CircleCI:
pytest tests/ -x -q --tb=short+py_compilelint + JSON validation - Vercel: frontend preview deploys
Common Issues
- Rate limiting on signup: Provision signup is limited to 2 requests per hour per IP. Use different test data or wait.
- Port already in use: Kill existing server process before restarting.
- MCP 406 error: Must include
Accept: application/json, text/event-streamheader. - OTel import errors: Ensure instrumentation packages match core SDK version (e.g., 0.62b1 pairs with 1.41.1).
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.
- 8d ago First seen · 80 lines · 39 tokens per session scan A baf089f1ac6c
testing-local-server is a skill published in the GitHub repository SunrisesIllNeverSee/agent-universe (1 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 742 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
pytest-suite
Write or extend the backend test suite following this project's conventions. Use when adding tests for a new service/route/repository, when coverage is missing, or when asked to test a feature. Knows the mocked-session + httpx AsyncClient setup so tests run with no database.
pytest
Skill "pytest" from bobmatnyc/claude-mpm-skills, covering pytest - professional python testing, basic pytest, with common plugins, for fastapi testing and for django testing.
validate-python-stack
Validate the Python Template repository or a project generated from it. Use before committing, publishing, deploying, or reviewing a stack to check catalog compilation, rendering, dependencies, formatting, tests, security workflows, skills, and representative runtime behavior.
add-vertical
Use this skill when adding a new feature vertical to this template — a domain aggregate with its port, repository, application service, DTOs, endpoint, and tests. Trigger it for requests like "add an endpoint", "add a new entity", "build the X feature", or "wire up a new service".
python-testing
Write or modify Python tests. Use when: adding new tests, understanding testing conventions, working with fixtures, writing FastAPI route tests, database tests, or following pytest patterns. DO NOT USE FOR RUNNING TESTS. If you are just running tests, not building them, you do not need this.
pytest
Skill "pytest" from bobmatnyc/claude-mpm, covering pytest - professional python testing, basic pytest, with common plugins, for fastapi testing and for django testing.