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 moyupeng0422/legal-tools --skill hermes-claude-codegit clone --depth 1 https://github.com/moyupeng0422/legal-toolsWrote 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/moyupeng0422/legal-tools/hermes-claude-code)<a href="https://agentmods.dev/skills/moyupeng0422/legal-tools/hermes-claude-code"><img src="https://agentmods.dev/badge/skills/moyupeng0422/legal-tools/hermes-claude-code/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/moyupeng0422/legal-tools/hermes-claude-code"><img src="https://agentmods.dev/badge/skills/moyupeng0422/legal-tools/hermes-claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00130 | $0.13559 |
| Opus 5 | $0.00065 | $0.06779 |
| Sonnet 5 | $0.00026 | $0.02712 |
| Haiku 4.5 | $0.00013 | $0.01356 |
Grade A, and why
hermes-claude-collaboration scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Python HTTP server + curl** → 成功（2.6MB 最终完成，耗时约 90s） The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
41 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.
- hermes-collab.md 9.4 KB
- LICENSE 1.0 KB
- README.md 4.7 KB
- references/acp-implementation.md 4.1 KB
- references/acp-research.md 18 KB
- references/active-discussion-protocol.md 1.9 KB
- references/batch-classification-hybrid.md 19 KB
- references/bulk-file-transfer.md 5.0 KB
- references/cc-context-file.md 8.1 KB
- references/cc-hook-data-schemas.md 4.0 KB
- references/cc-mcp-skill-dev-pattern.md 9.8 KB
- references/cc-perspective.md 7.2 KB
- references/cdp-browser-approach.md 3.3 KB
- references/cdp-handoff-template.md 2.4 KB
- references/comprehensive-analysis-pattern.md 1.4 KB
- references/design-discussion-method.md 2.2 KB
- references/doc-review-skill-design.md 9.7 KB
- references/edge-troubleshooting.md 2.4 KB
- references/environment-config.md 4.1 KB
- references/error-recovery.md 24 KB
- references/github-deployment.md 2.3 KB
- references/http-file-transfer.md 3.6 KB
- references/legal-article-collab-lessons.md 21 KB
- references/monitoring-debate.md 34 KB
- references/monitoring-mode.md 8.6 KB
- references/pitfalls.md 130 KB
- references/plan-review-pattern.md 2.0 KB
- references/rmfyalk-session-architecture.md 2.0 KB
- references/self-audit-findings.md 15 KB
- references/self-audit-protocol.md 2.3 KB
- references/session-lifecycle.md 17 KB
- references/skill-creation-workflow.md 23 KB
- references/ssh-diagnostics.md 5.5 KB
- references/ssh-reconnect-playbook.md 2.9 KB
- references/v3-protocol-test-results.md 4.1 KB
- scripts/add_toc.py 4.3 KB runs code
- scripts/extract_pitfalls.py 8.6 KB runs code
- scripts/rebuild_skill_md.py 5.6 KB runs code
- scripts/trim_pitfalls.py 3.1 KB runs code
- templates/acp_bootstrap.py 5.7 KB runs code
- templates/batch-verify.py 5.7 KB runs code
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.
- 11d ago First seen · 514 lines · 130 tokens per session scan A b424fcdc06d3
hermes-claude-collaboration is a skill published in the GitHub repository moyupeng0422/legal-tools (24 stars, last pushed 3d ago), with no licence file. It adds 130 tokens to every session and 13,559 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
executing-plans
Execution discipline that translates plans into tracked tasks with orchestration and verification loops. Use when driving a plan through cortex’s task system, coordinating workstreams across agents, or ensuring every plan item is tracked, executed, and verified.
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
review-code
Standalone code review for any scope — PR number, branch, file paths, or current changes. Synthesizes intent, runs 10 parallel specialized agents, and presents actionable findings with a verdict. For PR scope, optionally posts the review to GitHub with inline comments.
review-prs
Fetch and present a prioritized summary of all PRs awaiting the current user's review across the relevant projects and provide an interactive workflow helping the user phrase and post inline review comments and overall review decisions.