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 suyoumo/ClawProBench --skill content-creator-setupgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWrote 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/suyoumo/clawprobench/content-creator-setup)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/content-creator-setup"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/content-creator-setup/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/suyoumo/clawprobench/content-creator-setup"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/content-creator-setup.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 | $0.00047 | $0.02419 |
| Opus 5.5 | $0.00019 | $0.00968 |
| Sonnet 5.5 | $0.00009 | $0.00484 |
| Haiku 4.5 | $0.00005 | $0.00242 |
Grade A, and why
content-creator-setup 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 1mo 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Creator — Commitment System Setup
You are configuring the commitments system for a content creator. Their day involves:
- Morning: scanning trends and planning
- Midday: creating (writing, filming, recording)
- Afternoon: editing, thumbnails, publishing
- Evening: distribution across platforms, audience engagement
- Ideas arrive constantly and most won't be executed immediately
Persistence rules
For creator workflows, persistence comes before presentation.
- When the user asks to track a new content piece, update pipeline progress, add a deadline, capture a trend reaction, or log a sponsored obligation, you must write the corresponding workspace file before confirming success.
- Do not say a content item, trend response, distribution task, or sponsored
deadline was "tracked", "created", "queued", or "added to the pipeline"
unless the
memory_writesucceeded. - If the user asks only to track deadlines or commitments, do not generate assets, thumbnails, scripts, tweets, or video copy unless they explicitly ask for that creative work.
- Trend reactions like "create a short take on React compiler tonight" should
normally become active commitments in
projects/commitments/open/, not just prose or a suggestion.
Concrete examples:
- "Track this commitment: create a short take on the React compiler trend tonight."
Required behavior: write an active commitment under
projects/commitments/open/before confirming. - "Track this: the sponsored Figma workflow video has to ship by Friday."
Required behavior: write a sponsored commitment under
projects/commitments/open/. - "Track this commitment only: I need TikTok cuts and a Twitter thread for Episode 48 by tomorrow morning." Required behavior: write the deadline commitment(s); do not generate scripts, threads, or assets unless explicitly asked.
Companion skills
This bundle relies on these skills activating during conversation (keyword-triggered):
| Skill | Activates when | What it does |
|---|---|---|
commitment-triage |
User mentions obligations, deadlines | Extracts signals, creates/resolves commitments |
commitment-digest |
User asks "show commitments" | Composes formatted summary |
decision-capture |
User makes a decision | Records decision with rationale |
idea-parking |
User says "park this idea" | Parks ideas for weekly resurfacing |
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.
- 1mo ago First seen · 181 lines · 47 tokens per session scan A d59935ddaa20
content-creator-setup is a skill published in the GitHub repository suyoumo/ClawProBench (827 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 2,419 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
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
benchmark-design
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline, or import a published Benchmark package.
remote-claude-code
Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…
unified-llm-api
Call model APIs through @prismshadow/mmsp (MMSP) — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…