Borrowing it
Nothing to install: this file belongs to BenchBox-dev/BenchBox. 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/BenchBox-dev/BenchBox/develop/.claude/skills/shared-agent-execution/SKILL.mdgit clone --depth 1 https://github.com/BenchBox-dev/BenchBoxWrote 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/benchbox-dev/benchbox/shared-agent-execution)<a href="https://agentmods.dev/skills/benchbox-dev/benchbox/shared-agent-execution"><img src="https://agentmods.dev/badge/skills/benchbox-dev/benchbox/shared-agent-execution/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/benchbox-dev/benchbox/shared-agent-execution"><img src="https://agentmods.dev/badge/skills/benchbox-dev/benchbox/shared-agent-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00062 | $0.02292 |
| Opus 5.5 | $0.00025 | $0.00917 |
| Sonnet 5.5 | $0.00012 | $0.00458 |
| Haiku 4.5 | $0.00006 | $0.00229 |
Grade A, and why
agent-execution 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 4d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Execution
Use this component when another skill delegates work and needs a consistent workload role, reasoning effort, or agent harness configuration. The calling skill continues to own task decomposition, authorization, workspace isolation, and acceptance criteria.
This skill is a portable fallback for other agents and contexts. It never
overrides live OMP configuration. Precedence is: explicit user choice first,
then live OMP role aliases when they exist, then the portable defaults below.
review and research are custom OMP aliases, not automatic features: select
them explicitly or bind an agent to them. Portable callers select the workload
role themselves and translate its model through the harness reference.
Role @alias selectors (for example @review) resolve only when that alias
is configured in live OMP settings; otherwise dispatch the role's full
provider/model default, with --thinking auto on OMP.
Workload Roles
Roles describe workload fit, not a quality hierarchy. A role never auto-classifies a prompt, grants permissions, enters plan mode, enables an advisor, or guarantees independent review on its own.
| Role | Primary | Fallbacks, in order | Use for |
|---|---|---|---|
default |
anthropic/claude-sonnet-5-5:high |
openai-codex/gpt-6.1-sol:medium → muse-code/muse-spark-1.3-contributor:high → google-antigravity/gemini-3.8-flash:high |
Common implementation and management. |
smol |
openai-codex/gpt-6-luna:xhigh |
anthropic/claude-sonnet-5-5:medium → muse-code/muse-spark-1.3-contributor:medium → google-antigravity/gemini-3.8-flash:medium |
Simple, mechanical, and scouting work. |
slow |
anthropic/claude-fable-5:medium |
openai-codex/gpt-6-astra:high → muse-code/muse-wonder-1.0-contributor:xhigh → google-antigravity/gemini-4-argon:xhigh |
Maximum complexity and special cases. |
plan |
anthropic/claude-opus-5-5:xhigh |
openai-codex/gpt-6.1-sol:high → muse-code/muse-wonder-1.0-contributor:medium → google-antigravity/gemini-4-argon:medium |
Planning and high-capability analysis. |
review |
anthropic/claude-opus-5-5:medium |
openai-codex/gpt-6.1-sol:high → muse-code/muse-wonder-1.0-contributor:medium → google-antigravity/gemini-4-argon:medium |
Independent review; filter the author family. |
research |
anthropic/claude-opus-5-5:high |
openai-codex/gpt-6.1-sol:high → muse-code/muse-wonder-1.0-contributor:medium → google-antigravity/gemini-4-argon:medium |
High-capability research and synthesis. |
task |
anthropic/claude-sonnet-5-5:medium |
openai-codex/gpt-6.1-sol:medium → muse-code/muse-spark-1.3-contributor:high → google-antigravity/gemini-3.8-flash:high |
Common delegated implementation. |
commit |
openai-codex/gpt-6-luna:high |
anthropic/claude-sonnet-5-5:medium → muse-code/muse-spark-1.3-contributor:medium → google-antigravity/gemini-3.8-flash:medium |
Commit-message and changelog generation. |
vision |
google-antigravity/gemini-3.8-flash:high |
openai-codex/gpt-6.1-sol:medium → google-antigravity/gemini-3.8-flash:high → muse-code/muse-spark-1.3-contributor:medium |
Image-question helpers; not image generation. |
advisor |
anthropic/claude-fable-5:high |
openai-codex/gpt-6-astra:high → muse-code/muse-wonder-1.0-contributor:xhigh → google-antigravity/gemini-4-argon:xhigh |
Advisory second opinions when enabled. |
What ships with it
2 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.
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.
- 4d ago Changed · +11 lines 7108f67c7442
- 9d ago Changed · +39 lines · +2 tokens per session 96a3455f748e
- 28d ago Changed b1b9762f982c
- 1mo ago Changed · +2 lines e7aae4fee351
- 1mo ago First seen · 87 lines · 60 tokens per session scan A ef49342065c1
agent-execution is a skill published in the GitHub repository BenchBox-dev/BenchBox (12 stars, last pushed 21d ago), licensed MIT. It adds 62 tokens to every session and 2,292 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 2026-09-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…