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/ecro/harness-maker/test-skillnpx skills add Ecro/harness-maker --skill test-skillgit clone --depth 1 https://github.com/Ecro/harness-makerWhat 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 | $0.00036 | $0.00290 |
| Opus 5 | $0.00018 | $0.00145 |
| Sonnet 5 | $0.00007 | $0.00058 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
phase1-test-skill 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
Phase 1 Cross-Compat Test Skill
Verifies that harness-maker's .claude/skills/<name>/SKILL.md is recognized by both Claude Code and Cursor 2.4+ (which adopted the Anthropic SKILL.md standard).
Mission
When this skill is invoked, output exactly this single line and stop:
PHASE-1 A3 PASSED — skill loaded from .claude/skills/test-skill/ in <IDE-name>
Replace <IDE-name> with the current IDE.
No additional work. No tool calls.
Frontmatter cross-compat checkpoints
name(required) — kebab-case identifierdescription(required) — one-sentence summary used for auto-dispatchwhen_to_use— Anthropic standard trigger conditionuser-invocable: true— Anthropic standard, exposes the skill as a slash command
If both IDEs accept all four keys without strict-rejection AND auto-discovery fires on the trigger phrase, A3 passes.
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 · 32 lines · 36 tokens per session scan A d377694b0690
phase1-test-skill is a skill published in the GitHub repository Ecro/harness-maker (4 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 290 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 2026-08-31.
Other skills, from other repositories
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用，不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
chinese-code-review
中文 review 沟通参考——话术模板、分级标注（必须修复/建议修改/仅供参考）、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用，不要根据上下文自动触发。.
dispatching-parallel-agents
当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用.
executing-plans
当你有一份书面实现计划需要在单独的会话中执行，并设有审查检查点时使用.
verification-before-completion
在宣称工作完成、已修复或测试通过之前使用，在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功；始终用证据支撑断言.