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.
git clone --depth 1 https://github.com/alphaaiservice/cortexWrote 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/commands/alphaaiservice/cortex/perf-test)<a href="https://agentmods.dev/commands/alphaaiservice/cortex/perf-test"><img src="https://agentmods.dev/badge/commands/alphaaiservice/cortex/perf-test/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/commands/alphaaiservice/cortex/perf-test"><img src="https://agentmods.dev/badge/commands/alphaaiservice/cortex/perf-test.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 | $0.00048 | $0.13237 |
| Opus 5.5 | $0.00019 | $0.05295 |
| Sonnet 5.5 | $0.00010 | $0.02647 |
| Haiku 4.5 | $0.00005 | $0.01324 |
Grade C, and why
perf-test scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://localhost:8000/openapi.json 2>/dev/null | python3 -m json.tool 2>/dev/null | head -100 || echo "Server not running or no OpenAPI schema available" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:8000/openapi.json 2>/dev/null | python3 -m json.tool 2>/dev/null | head -100 || echo "Server not running or no OpenAPI schema available" How it starts
The opening of the file, as written. The whole thing — 1,558 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance & Load Testing Suite
Target: $ARGUMENTS (default: all endpoints, default users: 100, default duration: 60s)
Parse $ARGUMENTS for:
- target: specific endpoint path (e.g.,
/api/v1/users) orall - --users=N: number of virtual users (default: 100)
- --duration=Ns: test duration in seconds (default: 60s)
- --type=TYPE: test type —
smoke,load,stress,spike,soak(default:load) - --tool=TOOL: testing tool —
k6orlocust(default:k6) - --base-url=URL: API base URL (default: auto-detect from project config)
Step 1: Discover API Endpoints
Scan the project for all API endpoints, categorize them, and build an endpoint inventory.
1a: Find FastAPI Routers and Endpoints
echo "=== Scanning for FastAPI router files ==="
find . -name "*.py" -path "*/api/*" -o -name "*.py" -path "*/routes/*" -o -name "*.py" -path "*/routers/*" | head -50
echo ""
echo "=== Scanning for endpoint decorators ==="
grep -rn "@router\.\(get\|post\|put\|delete\|patch\|options\|head\)\|@app\.\(get\|post\|put\|delete\|patch\|options\|head\)" --include="*.py" . | head -100
echo ""
echo "=== Checking for OpenAPI schema ==="
grep -rn "openapi\|swagger\|/docs\|/redoc" --include="*.py" . | head -20
echo ""
echo "=== Checking for API prefix configuration ==="
grep -rn "prefix\s*=\s*['\"]" --include="*.py" . | grep -i "router\|api" | head -20
echo ""
echo "=== Checking for auth dependencies ==="
grep -rn "Depends.*auth\|Depends.*get_current_user\|Depends.*verify_token\|Depends.*require_role" --include="*.py" . | head -30
1b: Parse and Categorize Endpoints
For each discovered endpoint, extract:
- HTTP method (GET, POST, PUT, DELETE, PATCH)
- Full path (including router prefix)
- Auth requirement (public vs authenticated vs admin-only)
- Request body schema (if POST/PUT/PATCH — find Pydantic models)
- Path parameters and query parameters
- Response model
Categorize each endpoint:
- Public vs Authenticated: Does it have auth dependency injection?
- Read vs Write: GET/HEAD = read, POST/PUT/DELETE/PATCH = write
- Critical vs Non-Critical: Auth endpoints, payment endpoints, health checks = critical
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.
- 1mo ago First seen · 1,558 lines · 48 tokens per session scan C c87d0ec8cb79
perf-test is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 13,237 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
uat
Prepara o registra la UAT del entregable actual. Antes /alfred-dev:verify.
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
mutate
Run mutation testing to verify test quality. Builds a custom mutation tool or uses an existing framework, runs mutations, and reports the mutation score with surviving mutants.
test-audit
Use when writing, reviewing, or pruning tests. Three modes, one value bar: a four-question gate before any new test is written, a focused audit of one scope, and a campaign over a whole repo or subsystem that removes the least useful tests under a coverage guard. Every delete, merge, or repair carries written evidence…
lucius
Segunda opinión técnica externa vía Codex CLI — diagnóstico y prescripción por ítem.