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/markmhendrickson/neotoma/create_prnpx skills add markmhendrickson/neotoma --skill create_prgit clone --depth 1 https://github.com/markmhendrickson/neotomaWrote 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/markmhendrickson/neotoma/create_pr)<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/create_pr"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/create_pr.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 | $0.00098 | $0.03363 |
| Opus 5 | $0.00049 | $0.01682 |
| Sonnet 5 | $0.00020 | $0.00673 |
| Haiku 4.5 | $0.00010 | $0.00336 |
Grade A, and why
create_pr 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/create_pr — Standardized PR creation
When to invoke
- User says
/create_pror asks to open a PR. - Another skill (
/process_issues,/process_prs,/release,/fix_feature_bug) reaches the point of opening a PR. Call this skill rather than inlininggh pr create. - A worktree has a committed branch ready for review and no PR exists yet.
Do not invoke when amending an existing PR description — use gh pr edit directly with the same body conventions below.
Inputs
The caller (or the user) should provide, or this skill should infer:
- Branch — current branch (
git branch --show-current); if it equals the configured main branch, stop and ask. - Base branch — usually
main; for release work, the RC branch. - Linked issue(s) — GitHub issue number(s) the PR closes or refers to.
- Source plan / spec — Neotoma
planentity_id ordocs/path, if any. - Change classification — bug fix / feature / refactor / docs / release. Drives commit-style prefix in the title.
- Functional surface touched — CLI command/flag, MCP tool, HTTP endpoint, observable event, schema field, runtime knob, integration. Drives the docs-coverage check below.
Functional change documentation (mandatory for functional changes)
Every PR that changes user-observable behavior MUST ship thorough markdown documentation under docs/, and MUST surface it via the docs server (src/services/docs/) and the docs site (docs/site/pages/ via docs/site/site_doc_manifest.yaml). A PR that adds, removes, or changes any of the following counts as functional:
- A CLI command, subcommand, flag, env var, or output format
- An MCP tool name, parameter, or response shape
- An HTTP endpoint, request/response field, or error envelope field
- An entity_type schema field, relationship type, or canonical-name rule
- An observable event payload, metric name, or log structure
- A user-visible runtime config knob (timeout, header policy, allow-list)
- An integration/provider added or removed
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.
- 4d ago First seen · 242 lines · 98 tokens per session scan A d6da21234e4d
create_pr is a skill published in the GitHub repository markmhendrickson/neotoma (31 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 3,363 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 2026-08-30.
Other skills, from other repositories
security-observability
只读查询 agent-sec-cli 已落盘的历史安全事件记录，并据此生成会话级安全复盘。仅当用户显式要求查看或审计已发生的安全事件、安全告警、安全审计记录，或要求按 session/run/trace/时间/类别筛选与统计已有安全事件，或要求复盘某次会话的安全判定时使用。不用于扫描新内容：检查代码安全性用 code-scanner，检测 prompt 注入用 prompt-scanner，审查 Skill 安全状态用 skill-ledger。不要因为对话中出现“安全”“工具调用”等字样、或为了主动自查而触发。.
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
pr-body
分析当前分支的全部变更，自动生成或更新 PR 标题和正文。聚焦内容质量：解释 why、归纳 what、标注测试方式，遵循 anolisa 项目 PR 模板规范。适用于新建 PR 前生成描述，或已有 PR 需要更新描述。.
install-openclaw
Install and configure OpenClaw non-interactively with Alibaba Cloud Model Studio. Use when the user asks to install OpenClaw, configure Aliyun Bailian/Model Studio/DashScope credentials, choose pay-as-you-go, Coding Plan, or Token Plan billing, set Base URL/model config, optionally configure DingTalk, start the local…
prompt-scanner
使用 agent-sec-cli 扫描 prompt 文本中的注入攻击和越狱尝试，返回结构化 JSON 扫描结果。当用户提到 prompt 安全、prompt 注入检测、越狱检测、提示词攻击检测，或者需要判断一段文本是否包含恶意 prompt 注入时，都应使用此技能。即使用户没有明确说"扫描"，只要涉及评估 prompt 文本的安全性，也应触发此技能。.
agentsight-bugfix
AgentSight fix issues 流程。了解问题 → 复现验证 → 根因分析 → 编码修复 → 验证修复，五阶段标准化调试迭代循环。确保 AI agent 遵循最小改动、逐轮验证的修复规范。.