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 agentmods add commands/oxi-717/ai-native-toolkit/loadtestgit clone --depth 1 https://github.com/OXI-717/ai-native-toolkitWhat 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 | $0.00031 | $0.00853 |
| Opus 5 | $0.00015 | $0.00426 |
| Sonnet 5 | $0.00006 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
loadtest 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 2d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/loadtest — HTTP load test
Runs the loadtest skill against a URL. Locust-based, time-bounded, bounded-concurrency.
Arguments
Input: $ARGUMENTS
<url>(required) — base URL.--users N— concurrent virtual users. Default20.--spawn-rate R— users spawned per second. Default2.--duration Tm— run length, e.g.2m,5m,30m. Default2m.--wait-min S/--wait-max S— per-user wait between requests, in seconds. Default1/2(≈ 0.5–1 req/s/user). Set both to0to remove the cap (advanced — use with care, may overwhelm small targets and balloon serverless billing).--lang ru|en— report language. Default: match user's language.
Flow
- Parse URL and load profile from $ARGUMENTS.
- Print billing warning if the URL looks serverless (Vercel / Cloudflare Workers / AWS Lambda / GCP Cloud Run).
- Ask user for endpoints + auth method if not obvious from bundle. For Telegram mini apps, read the initData from
secrets.env. - Invoke loadtest skill:
- Render
locustfile.pyfrom template. - Smoke-check each endpoint with 1 request.
- Run Locust headless for the requested duration.
- Generate
REPORT.mdfrom CSV stats.
- Render
- Print the absolute path to
REPORT.mdandreport.html(Locust's own dashboard).
Examples
/loadtest https://api.example.com
/loadtest https://api.example.com --users 50 --duration 5m
/loadtest https://target.example --users 10 --duration 1m --lang ru
/loadtest https://api.example.com --users 200 --duration 10m --wait-min 0 --wait-max 0
Rules
- Never run without explicit duration and user count.
- Always print the billing warning for serverless targets before starting.
- Stop if error rate crosses 20% or the target returns consecutive 5xx for > 30 s.
- Default per-user wait is 1–2s (caps to ~10–20 RPS at 20 users). Only set
--wait-min 0 --wait-max 0if user explicitly accepts the risk. - Never load-test an endpoint you haven't smoke-tested first.
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.
- 2d ago First seen · 71 lines · 31 tokens per session scan A 60456ea59765
loadtest is a command published in the GitHub repository OXI-717/ai-native-toolkit (7 stars, last pushed 10d ago), licensed MIT. It adds 31 tokens to every session and 853 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.