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/nickguai/herd/write-new-skillnpx skills add NickGuAI/Herd --skill write-new-skillgit clone --depth 1 https://github.com/NickGuAI/HerdWrote 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/nickguai/herd/write-new-skill)<a href="https://agentmods.dev/skills/nickguai/herd/write-new-skill"><img src="https://agentmods.dev/badge/skills/nickguai/herd/write-new-skill.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.00849 |
| Opus 5 | $0.00026 | $0.00425 |
| Sonnet 5 | $0.00011 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
write-new-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 5d 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
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
2 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.
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.
- 5d ago First seen · 99 lines · 53 tokens per session scan A 965e81c8f1e1
write-new-skill is a skill published in the GitHub repository NickGuAI/Herd (17 stars, last pushed 24d ago), licensed AGPL-3.0. It adds 53 tokens to every session and 849 once invoked, about $0.0003 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
setup
Configure or diagnose Hames in the current project when the user invokes /setup.
go
Execute an approved Hames task contract when the user invokes /go.
ready
Prepare and approve a bounded task contract when the user invokes /ready.
doctor
Diagnose a Hames installation without changing it when the user invokes /doctor.
endy-delegate
Use this skill when a task is best handed off to another coding agent in the endy stack — OpenCode (multi-model worker, fast refactors, test writing), CommandCode/cmd (Kimi K2.6 / DeepSeek), Hermes (Nous Research, tool-heavy), Gemini, or Claude. Covers three delivery modes: short blocking calls, long detached tmux…
endy-state
Use this skill when you need to inspect the endy environment of a running task — handoff lineage (who handed work to whom and why), peers in the same and other endy sessions, and per-agent tier headroom (codex 5h/wk, opencode session cost) so you can pick the next agent to hand off to. The same data is auto-prepended…