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 magnus919/agent-skills --skill llama-cppgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/llama-cpp)<a href="https://agentmods.dev/skills/magnus919/agent-skills/llama-cpp"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/llama-cpp/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/magnus919/agent-skills/llama-cpp"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/llama-cpp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 21 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00122 | $0.01908 |
| Opus 5 | $0.00061 | $0.00954 |
| Sonnet 5 | $0.00024 | $0.00382 |
| Haiku 4.5 | $0.00012 | $0.00191 |
Grade A, and why
llama-cpp 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 9d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llama.cpp Operations
Treat every launch recipe as a hypothesis about a specific build, model, host, and workload. Discover capabilities from the installed binary, inspect the model and startup logs, then measure the requested boundary.
Operating contract
- Record the exact llama.cpp version or commit, installation method, OS and architecture, CPU and RAM, accelerator and memory, driver/toolkit, available devices, model provenance and quantization, intended context, concurrency, and workload.
- Read the installed command's
--helpbefore using a flag from documentation. llama.cpp flags, defaults, binary names, and REST behavior change frequently. - Confirm the target, scope, and rollback path before acting. Read-only discovery may proceed without confirmation.
- Verify the backend from
--list-devicesand model-load logs. A successful build or an accepted GPU flag does not prove acceleration is active. - Start with a bounded CLI smoke test on loopback or local input. Establish a measured baseline before changing threads, batches, context, cache types, offload, or split mode.
- Call work complete only at the requested boundary: binary, model load, generated output, API response, benchmark comparison, or diagnosed failure with evidence.
When not to use
Use ml-engineering for model training, fine-tuning, broad quantization methodology, evaluation design, or choosing among llama.cpp, vLLM, TGI, and other engines. Use the relevant product skill for Ollama, LM Studio, or LlamaIndex. Use binding-specific documentation for llama-cpp-python, node-llama-cpp, or other language wrappers.
Read-only preflight
Run only commands that exist in the installed build:
llama-cli --version
llama-cli --help
llama-cli --list-devices
llama-server --version
llama-server --help
llama-bench --help
Also inspect host memory and accelerator state with native OS/vendor tools. Record results in the operation record. If no binary exists, choose an installation path only after reading installation and backends.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 7.0 KB
- EVIDENCE-LEDGER.md 4.8 KB
- README.md 3.2 KB
- references/inference-and-serving.md 5.2 KB
- references/installation-and-backends.md 5.2 KB
- references/models-gguf-and-memory.md 5.2 KB
- references/performance-and-benchmarking.md 5.0 KB
- references/source-index.md 7.1 KB
- references/troubleshooting.md 5.5 KB
- templates/benchmark-comparison.md 1.3 KB
- templates/operation-record.md 1.2 KB
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.
- 9d ago First seen · 95 lines · 122 tokens per session scan A e6e06e2f7c0e
llama-cpp is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 1,908 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
map
Build and commit a Cortex function knowledge graph — maps structural dependencies and domain intent relationships across all AI functions in the project. Supports --reduce (default on) for transitive reduction of the dependency graph.
test
Enter the Test phase of CocoBrew. Reads spec.md test requirements, generates test cases, executes SQL validation and quality checks, records results in test.md. Can be re-run without full rebuild. Requires Build phase completion.
map-diff
Analyze the impact of staged git changes against the committed Cortex function knowledge graph — shows which downstream functions are affected before you commit.
map-explain
Produce a natural-language explanation of a specific Cortex function, business capability, or schema element from the committed knowledge graph.
trace-health
Compute CocoTrace Snowflake asset health grade. Usage: $trace health.
neurolink-guide
Guide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features.