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 project-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/project-setup)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/project-setup"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/project-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/project-setup"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/project-setup.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 Data Exfiltration · line 37 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00030 | $0.00830 |
| Opus 5.5 | $0.00012 | $0.00332 |
| Sonnet 5.5 | $0.00006 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
project-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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Setup
Add a new GitHub repository as a tracked project in the workspace and install workflow automation.
Step 1: Parse the repo
Extract owner/repo from the user's message. If ambiguous, ask. Validate via GitHub API: http(method="GET", url="https://api.github.com/repos/{owner}/{repo}"). If 404 or no access, tell the user.
Step 2: Quick setup (3 questions, no timezone)
- Who are the maintainers/reviewers? (default: the user's GitHub handle)
- Do you use a staging branch? What's it called? (default: no staging; use
stagingif yes) - Any AI agents creating PRs? (e.g. Dependabot, Copilot, internal bots) (default: none)
Read main_branch from the API response's default_branch field.
Step 3: Create project in workspace
Write projects/<owner>-<repo>/project.md:
---
type: project
repo: <owner/repo>
added_at: <today YYYY-MM-DD>
maintainers: [<handles>]
main_branch: <branch from API>
staging_branch: <branch or null>
ai_agent_authors: [<bot handles>]
workflow_installed: false
---
# <owner/repo>
<description from API response>
## Workflow missions
(populated after install)
Write projects/<owner>-<repo>/notes.md:
# Notes: <owner/repo>
Developer notes for this project. Searchable via memory_search.
Step 4: Install workflow missions
Follow the github-workflow skill's install procedure. For each of the 6 mission templates in github-workflow/references/workflow-routines.md:
- Replace
{{repository}}withowner/repo - Replace
{{slug}}with<owner>-<repo> - Replace
{{maintainers}}with the maintainer list - Replace
{{main_branch}}and{{staging_branch}}with the configured branches - Replace
{{batch_interval_hours}}with8(default) - Call
mission_create(name, goal, cadence)for each
If staging_branch is null, skip wf-staging-review-<slug>.
After installing, update the project file:
- Set
workflow_installed: true - List the installed mission names under
## Workflow missions
Step 5: Confirm
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 · 104 lines · 30 tokens per session scan A c5632d7ee11c
project-setup is a skill published in the GitHub repository suyoumo/ClawProBench (827 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 830 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
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…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.
company-hr
Run HR for a PenguinHarness organization — guarantee every employee has an enabled calendar event, hire and offboard employees (channels included), evaluate and improve them (with the default-rsi-toolkit plugin's agent-optimization skill), and keep the handbook's role conventions current.
company-mirror
Run a PenguinHarness organization that mirrors a real company — one digital twin per real colleague, each twin's desk bound to that colleague's chat bot, twins answering what the handbook already knows and relaying the rest to one another instead of hiring, scheduling and filing tickets.
company-setup
Create a company-mode organization together with the user — collect its id, name, mission, shared workspace, model and CEO budget one question at a time, confirm the whole thing in one summary, then run penguin org create and hand the user over to company mode.
meta-issue-to-pr-autopilot
Triages an issue, delegates the fix to sub-agent, drafts a PR description with summarize, and opens the PR via gh. Best used on small, well-scoped issues with clear acceptance criteria.