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 agentmods add skills/suyoumo/clawprobench/project-setupnpx skills add suyoumo/ClawProBench --skill project-setupgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWhat 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 | $0.00030 | $0.00830 |
| Opus 5 | $0.00015 | $0.00415 |
| Sonnet 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 2d 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.
- 2d ago First seen · 104 lines · 30 tokens per session scan A c5632d7ee11c
project-setup is a skill published in the GitHub repository suyoumo/ClawProBench (823 stars, last pushed 8d ago), licensed Apache-2.0. It adds 30 tokens to every session and 830 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
lastlight-evals
Scaffold, configure and run a Last Light EVALS workspace — the harness that runs Last Light's real workflows against a mocked GitHub and grades them deterministically. Use when the user wants to "set up / scaffold Last Light Evals", "create an evals workspace or instance", "run evals", "compare models", or author new…
issue-comment
Handle a non-build maintainer comment on an issue or PR — close, reopen, label, dedupe, answer a brief question, or triage. Action-only; redirect anything that needs code changes to /build.
chat
Conversational assistant for messaging-platform threads (Slack, Discord). Answer questions about repos, PRs, and issues, explain code, and guide users to the natural-language workflow triggers listed in the system prompt.
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
perpetuum
为一个或多个项目建立、运行和管理长期 Agent 队伍。适用于初始化长期自主工作、按项目 cron 计划持续推进 Story、查看或调整 Story 看板，以及处理人类输入。.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.