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 vinnie357/claude-skills --skill runexgit clone --depth 1 https://github.com/vinnie357/claude-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/vinnie357/claude-skills/runex)<a href="https://agentmods.dev/skills/vinnie357/claude-skills/runex"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/runex/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/vinnie357/claude-skills/runex"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/runex.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 | $0.00056 | $0.02876 |
| Opus 5 | $0.00028 | $0.01438 |
| Sonnet 5 | $0.00011 | $0.00575 |
| Haiku 4.5 | $0.00006 | $0.00288 |
Grade A, and why
runex 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 5d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runex Workflow Engine
Runex is a single-binary Elixir workflow orchestrator. It parses TOML (primary) and YAML workflow definitions, builds a DAG of steps, and executes them via pluggable drivers. It runs in standalone mode (SQLite, default — no configuration required) or federated mode (Postgres + libcluster) for multi-node deployments.
Verified against lib/runex/driver.ex's @drivers map (single source of truth for valid driver = values, Runex.Driver.names/0) — 14 registered drivers:
- command:
shell, mise, nushell - agent:
agent, altana, awman, codex, antigravity, claude - workflow:
workflow, runex(moduleRunex.Drivers.RunexSub) - container:
container, flame - wasm:
wasm
The 14 names are the flat @drivers map; the class labels above come from
execution_class/1's module doc comment, not from the function's actual runtime
behavior — that function's "workflow" guard clause matches
the literal string "runex_sub", not the registered driver name "runex", so
execution_class("runex") actually falls through to "other". This looks like an
upstream naming-drift bug (the guard clause not being updated when the driver was
registered as "runex" rather than "runex_sub"), not a documentation error here.
Current documented version: 0.0.7 (mix.exs @version). Legacy templates for older deployments remain under templates/0.1.0/ and scripts/0.1.0/.
Anti-fabrication
This skill follows core:anti-fabrication. Runex is a workspace-owned strategic surface
with the fastest cadence this marketplace documents, so every claim above the fold is
checked against the source tree rather than release notes. Verified against runex
0.0.7 (mix.exs @version, re-confirmed 2026-08-04, claude-skills-223): the driver list
was corrected from 8 to the real 14 registered in Runex.Driver.@drivers, and workflow
path resolution was corrected from 3 to the real 4 search roots in Paths.workflows_dirs/ 0. A Gate 3 pass then caught the execution_class/1 naming-drift documented above as an
upstream bug, not a doc error (filed separately, claude-skills-239). Re-verify against
the live lib/runex/driver.ex and mix.exs @version before asserting a driver name or
version this skill doesn't cover — this is the fastest-moving source in the repo.
What ships with it
12 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.
- references/bundle-build-rules.md 3.2 KB
- references/bundles.md 9.7 KB
- references/debugging.md 6.2 KB
- scripts/0.0.7/bundles.nu 9.2 KB
- scripts/0.0.7/debug.nu 6.5 KB
- scripts/0.0.7/runex.nu 5.8 KB
- scripts/0.1.0/bundles.nu 7.2 KB
- scripts/0.1.0/debug.nu 5.4 KB
- scripts/0.1.0/runex.nu 4.1 KB
- templates/0.0.7/api.md 19 KB
- templates/0.0.7/mise.toml 43 B
- templates/0.1.0/api.md 7.3 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.
- 5d ago First seen · 211 lines · 56 tokens per session scan A 36b0b30b123a
runex is a skill published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 2,876 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.