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/vibhasdutta/loop-engineer/hermesnpx skills add vibhasdutta/loop-engineer --skill hermesgit clone --depth 1 https://github.com/vibhasdutta/loop-engineerWhat 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 | $0.00105 | $0.03298 |
| Opus 5 | $0.00053 | $0.01649 |
| Sonnet 5 | $0.00021 | $0.00660 |
| Haiku 4.5 | $0.00011 | $0.00330 |
Grade A, and why
loop-engineer 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
42 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/agent-factory.md 2.1 KB
- agents/auditor.md 2.1 KB
- agents/executor.md 2.8 KB
- agents/knowledge-sources.md 6.4 KB
- agents/knowledge-sources/01-search-engines.md 237 B
- agents/knowledge-sources/02-open-source-code.md 255 B
- agents/knowledge-sources/03-official-documentation.md 460 B
- agents/knowledge-sources/04-package-managers.md 258 B
- agents/knowledge-sources/05-research-papers.md 336 B
- agents/knowledge-sources/06-ai-machine-learning.md 322 B
- agents/knowledge-sources/07-apis.md 144 B
- agents/knowledge-sources/08-community-discussions.md 271 B
- agents/knowledge-sources/09-tutorials-learning.md 245 B
- agents/knowledge-sources/10-cybersecurity.md 210 B
- agents/knowledge-sources/11-system-design.md 181 B
- agents/knowledge-sources/12-business-startups.md 220 B
- agents/knowledge-sources/13-marketing.md 152 B
- agents/knowledge-sources/14-sales-lead-generation.md 246 B
- agents/knowledge-sources/15-jobs-careers.md 145 B
- agents/knowledge-sources/16-design.md 190 B
- agents/knowledge-sources/17-images.md 124 B
- agents/knowledge-sources/18-videos.md 125 B
- agents/knowledge-sources/19-books.md 127 B
- agents/knowledge-sources/20-news.md 149 B
- agents/knowledge-sources/21-government.md 156 B
- agents/knowledge-sources/22-finance.md 153 B
- agents/knowledge-sources/23-legal.md 112 B
- agents/knowledge-sources/24-medical.md 82 B
- agents/knowledge-sources/25-science.md 99 B
- agents/knowledge-sources/26-geography.md 87 B
- agents/knowledge-sources/27-shopping.md 119 B
- agents/knowledge-sources/28-social-media.md 194 B
- agents/knowledge-sources/29-wikis.md 103 B
- agents/knowledge-sources/30-domain-website-intelligence.md 295 B
- agents/knowledge-sources/31-datasets.md 159 B
- agents/knowledge-sources/32-file-types.md 270 B
- agents/knowledge-sources/33-browser-capabilities.md 461 B
- agents/memory-keeper.md 1.7 KB
- agents/planner.md 1.8 KB
- agents/researcher.md 6.0 KB
- agents/resource-scout.md 3.9 KB
- HERMES.md 3.0 KB
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 · 233 lines · 105 tokens per session scan A 49b0790b90db
loop-engineer is a skill published in the GitHub repository vibhasdutta/loop-engineer (3 stars, last pushed 1mo ago), with no licence file. It adds 105 tokens to every session and 3,298 once invoked, about $0.0005 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
agent-team
产品经理与项目管理专家在应对复杂项目时，使用此技能可动态组建包含“执行、指挥、评审”的专属AI团队。实时查看多智能体辩论与决策全过程，共享统一上下文记忆，一键完成从会议决策到系统构建的全流程高效协同！.
antinet-provenance
软件开发工程师与信息安全分析师在构建多智能体系统时，当需全链路可观测与安全审计，请用此技能。它自动收集操作日志，生成可追溯证据链与向量索引，开箱即用实现系统审计与精准回放，让Agent运行安全透明。.
provenance
收集系统全链路操作日志，生成可追溯的执行证据链与向量索引，是多智能体系统可观测性与安全审计的底座。.
handoff
Compact current session context into a handoff document for seamless continuation in a new session. Use when context window is exhausted, switching machines, handing work to another agent, or ending a long session mid-task.
supergraph
Meta-orchestrator — dispatches to the right skill for the task. Use before any non-trivial work.
idd-spec-audit
Repo-local, dogfood-only semantic audit of the IDD instruction corpus for leaked session context, cross-file contradictions, fresh-memory completability gaps, automation blockers, and restatement-discipline drift. Use only in the kurone-kito/idd-skill source repository, on request, to audit .github/instructions…