Paddler is an open-source service that runs and distributes large language model and vision-language model inference across self-managed CPU or GPU infrastructure. It is for product, DevOps, and LLM operations teams that need private, scalable model serving, embeddings, and more predictable costs. The catalogue add-ons help agents operate Paddler.
Borrowing it
Nothing to install: this file belongs to intentee/paddler. 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/intentee/paddler/main/.claude/skills/running-coverage/SKILL.mdgit clone --depth 1 https://github.com/intentee/paddlerWrote 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/intentee/paddler/running-coverage)<a href="https://agentmods.dev/skills/intentee/paddler/running-coverage"><img src="https://agentmods.dev/badge/skills/intentee/paddler/running-coverage/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/skills/intentee/paddler/running-coverage"><img src="https://agentmods.dev/badge/skills/intentee/paddler/running-coverage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.00425 |
| Opus 5.5 | $0.00017 | $0.00170 |
| Sonnet 5.5 | $0.00008 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
running-coverage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Running the code coverage
Run every test suite in the workspace, picking the fastest compiled device backend for the host, then report the workspace code coverage.
Step 1: detect the device
Run this once at the start and echo the chosen device:
if [[ "$OSTYPE" == "darwin"* ]]; then
DEVICE=metal
elif command -v nvidia-smi >/dev/null 2>&1 && nvidia-smi >/dev/null 2>&1; then
DEVICE=cuda
else
DEVICE=cpu
fi
echo "Device: $DEVICE"
$DEVICE selects the Paddler binary and the Rust feature set every suite in Step 2 runs against.
Step 2: run the code coverage
Copy this checklist and tick each item as the suite completes:
- [ ] Rust
- [ ] Python client
- [ ] JS client
| # | Suite | Command (from the repo root) |
|---|---|---|
| 1 | Rust | TEST_DEVICE=$DEVICE make test.coverage |
| 2 | Python client | TEST_DEVICE=$DEVICE make test.client.python.coverage |
| 3 | JS client | TEST_DEVICE=$DEVICE make test.client.js.coverage |
Step 3: rules during the run
- Serialize GPU suites. When
$DEVICEiscudaormetal, run test suites sequentially to avoid device contention. - Per-test 30 s budget. Flag any individual test that exceeds 30 s wall-clock. That is a real bug — production or test — not flakiness.
Step 4: report
After the coverage suite finishes, sum up the results in an actionable report.
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.
- 23d ago Changed · +10 lines 861c3c319fb1
- 2mo ago First seen · 41 lines · 42 tokens per session scan A c88230a640c5
running-coverage is a skill published in the GitHub repository intentee/paddler (1,685 stars, last pushed 3d ago), licensed Apache-2.0. It adds 42 tokens to every session and 425 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 2026-08-30.
Other skills, from other repositories
promptfoo-redteam-run
Execute, inspect, and rerun an existing Promptfoo redteam scan. Use for generated YAML, result exports, attack success rates, grader/target errors, filtered reruns, and CI gates. Use promptfoo-provider-setup for connections and promptfoo-redteam-setup for new scan plans.
promptfoo-redteam-setup
Create or refine a Promptfoo redteam config and generate probes from target behavior, code, or OpenAPI evidence. Use for purpose, trust boundaries, plugins, strategies, and grading guidance. Use promptfoo-provider-setup for connection work and promptfoo-redteam-run for an existing scan.
promptfoo-provider-setup
Connect Promptfoo to a model, live HTTP API, local Python/JavaScript provider, or app code. Use for request/auth mapping, response parsing, OpenAPI setup, and connection smoke tests. Use promptfoo-evals for broader eval coverage and promptfoo-redteam-setup for attack selection.
discount-review
Inspect the discount policy fixture with a repeatable review checklist and helper script.
code-review
Reviews code for bugs, security issues, and best practices.
token-skill
Use this skill when the user explicitly asks to use token-skill and wants the special token.