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 MemTensor/skills-vote --skill skills-vote-localgit clone --depth 1 https://github.com/MemTensor/skills-voteWrote 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/memtensor/skills-vote/skills-vote-local)<a href="https://agentmods.dev/skills/memtensor/skills-vote/skills-vote-local"><img src="https://agentmods.dev/badge/skills/memtensor/skills-vote/skills-vote-local/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/memtensor/skills-vote/skills-vote-local"><img src="https://agentmods.dev/badge/skills/memtensor/skills-vote/skills-vote-local.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 | $0.00028 | $0.00323 |
| Opus 5.5 | $0.00011 | $0.00129 |
| Sonnet 5.5 | $0.00006 | $0.00065 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
skills-vote-local 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 2mo 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
Skills Vote Local
Read only this file first. Do not read scripts/, docs/, or any other files in this skill unless this file or a script output explicitly tells you to do so.
Use this skill when the current task needs skill discovery from a local or private skill library instead of a network service.
All paths mentioned in this file are relative to this skill root. cd to this root directory before running any command here.
Run:
uv run -qq scripts/route_prompt.py --role main
Then follow the rendered stdout exactly.
If routing.mode selects a subagent route, the user configuration explicitly requests subagent-based skill lookup. The main agent should use subagent delegation when the current host/tooling permits it.
Do not use fallback merely because the current user message did not repeat "use subagent".
If the current host, tool policy, runtime, or authorization model cannot create a subagent in this turn, run:
uv run -qq scripts/route_prompt.py --role main --fallback
Then follow the fallback stdout exactly.
If you are a subagent and you read this file directly, do not run this command with --role main. Run:
uv run -qq scripts/route_prompt.py --role subagent
Then follow the rendered stdout exactly.
What ships with it
13 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.
- configs/config.yaml.example 1.6 KB
- docs/config-schema.md 6.4 KB
- docs/handoff.md 928 B
- scripts/check_env.py 5.9 KB runs code
- scripts/chroma_utils.py 3.5 KB runs code
- scripts/cli_common.py 932 B runs code
- scripts/config_validation.py 2.7 KB runs code
- scripts/index.py 771 B runs code
- scripts/local_skill_search.py 22 KB runs code
- scripts/prompt.py 28 KB runs code
- scripts/recommend.py 1.1 KB runs code
- scripts/route_prompt.py 15 KB runs code
- scripts/sync_skills.py 8.1 KB runs code
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.
- 2mo ago First seen · 44 lines · 28 tokens per session scan A 51247237dc25
skills-vote-local is a skill published in the GitHub repository MemTensor/skills-vote (307 stars, last pushed 28d ago), licensed MIT. It adds 28 tokens to every session and 323 once invoked, about $0.0001 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
LEAP
LEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skills into one. It is called by the main SkillAlchemy workflow. Use when SkillAlchemy requires distillation or fusion.
agentsop-dspy
Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Activate when the user says any of: "use DSPy", "compile a prompt", "optimize prompts/programs", "MIPRO/MIPROv2", "BootstrapFewShot", "GEPA", "Signatures + Modules", "teleprompter", "auto-tune prompts…
agentsop-langgraph
Decision protocol for building, debugging, and operating LangGraph-based agent systems. Activates when a coder agent is asked to design a stateful LLM workflow, add human-in-the-loop, choose a multi-agent pattern (supervisor / swarm / hierarchical), pick a checkpoint backend, or migrate a fragile chain into a durable…
agentsop-llm-tool-idempotency
Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op instead of a double-send. The load-bearing premise: the LM cannot promise it'll call exactly once; the tool must promise…
agentsop-map-reduce-fanout
Decision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each item in parallel, then combine". Activates when the coder agent is about to process N items with N LM calls (per-doc summarize, per-query retrieve, per-candidate rank, parallel tool fan-out). Encodes…
agentsop-output-format-by-model
Pick an LM output format per (task x consumer x model) rather than by reflex: different formats carry different cognitive load (e.g. code-in-JSON makes the same model write worse code than plain-text+diff, while asking for prose when you need a typed object fails the other way). Use when designing or debugging an LM's…