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/zeromadlife/sage-agent/commitnpx skills add ZeroMadLife/sage-agent --skill commitgit clone --depth 1 https://github.com/ZeroMadLife/sage-agentWhat 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 | $0.00010 | $0.00089 |
| Opus 5 | $0.00005 | $0.00044 |
| Sonnet 5 | $0.00002 | $0.00018 |
| Haiku 4.5 | $0.00001 | $0.00009 |
Grade A, and why
commit 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.
What it actually says
请准备本次提交：
- 用 run_shell 跑
git status和git diff --staged - 总结改动内容
- 建议 commit message（中文，遵循 conventional commits）
- 不要实际执行 git commit，只给建议
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 · 12 lines · 10 tokens per session scan A 164c5a0fe2ad
commit is a skill published in the GitHub repository ZeroMadLife/sage-agent (9 stars, last pushed 7d ago), licensed MIT. It adds 10 tokens to every session and 89 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
ai-video-studio-backend-test
Backend validation workflow for ai-video-studio. Use when changing FastAPI endpoints, services, repositories, models, migrations, prompts, task orchestration, or when diagnosing pytest failures. Chooses between quick, full, targeted, and diagnostic backend checks while treating AGENTS.md…
ai-video-studio-mcp-e2e
Chrome DevTools E2E workflow for ai-video-studio. Use when a change affects login, frontend/backend integration, AI generation, image or video flows, or any user-visible path that AGENTS.md requires to be verified in a real browser. Reads AGENTS.md for the current validation policy and account, follows the shared…
ai-video-studio-frontend-test
Frontend validation workflow for ai-video-studio. Use when changing Next.js pages, components, hooks, API client code, route guards, auth flows, or when deciding whether lint, tests, build, and browser verification are required. Chooses between mandatory lint, conditional frontend tests, and risk-driven builds while…
Review a GitHub PR (via gh)
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Implement (multi-agent loop)
Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.
Best of N (parallel attempts)
Delegate N parallel subagents on the same task, then pick the best result.