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 Negai-ai/AgentClaw --skill agentclaw_apigit clone --depth 1 https://github.com/Negai-ai/AgentClawWrote 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/negai-ai/agentclaw/agentclaw_api)<a href="https://agentmods.dev/skills/negai-ai/agentclaw/agentclaw_api"><img src="https://agentmods.dev/badge/skills/negai-ai/agentclaw/agentclaw_api/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/negai-ai/agentclaw/agentclaw_api"><img src="https://agentmods.dev/badge/skills/negai-ai/agentclaw/agentclaw_api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.01557 |
| Opus 5.5 | $0.00023 | $0.00623 |
| Sonnet 5.5 | $0.00011 | $0.00311 |
| Haiku 4.5 | $0.00006 | $0.00156 |
Grade A, and why
agentclaw_api 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 2mo 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.
- **工具选择**: 调用 API 时使用 `python` 或 `shell` 工具发送 HTTP 请求（例如 `requests.post()`、`curl`）。 How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentClaw 平台 API 使用指南
Read this file first. Read references/* only when需要操作具体模块时。
何时使用 agentclaw_api
- 用户请求可以由已注册的 AgentClaw workflow/agent 能力完成，例如运行、触发、查询或续传已有工作流。
- 用户要创建、查询、更新、删除、暂停、恢复或立即触发定时任务。
- 用户说“每天/每小时/定期/周期性/cron/自动运行某个工作流或智能体”。
- 用户要把已经创建的工作流接入平台运行能力，例如热注册工作流文件、调用工作流、配置调度、查看执行历史。
- 用户要通过平台 API 管理知识库、渠道、对话、文件、提示词、模型、追踪日志。
定时任务相关操作请读取 references/scheduler.md，创建任务使用 POST /api/scheduler/jobs。
调用方式
- 入口:
{BASE_URL}是服务启动时写入<project_dir>/.agentclaw/relay.json的internal_url。它是独立本机 internal relay 地址，通常不同于主服务端口。 - 备用入口: 环境变量
AGENTCLAW_INTERNAL_URL也可提供同一个本机 relay 地址。 - 认证: 所有内部 agent/shell 请求通过
/_internal/前缀访问，relay 会在服务端完成认证。请求只需要业务 payload 和Content-Type: application/json。 - 拼接规则:
{BASE_URL}/_internal+ 文档路径。文档里的/api/...、/admin/...是目标路径，不是最终 URL。 - 工具选择: 调用 API 时使用
python或shell工具发送 HTTP 请求（例如requests.post()、curl）。
| 文档路径 | 实际调用路径 |
|---|---|
/api/workflow/run |
{BASE_URL}/_internal/api/workflow/run |
/admin/knowledgebases |
{BASE_URL}/_internal/admin/knowledgebases |
/api/scheduler/jobs |
{BASE_URL}/_internal/api/scheduler/jobs |
入口读取示例
import json
import os
from pathlib import Path
project_dir = Path(os.getenv("AGENTCLAW_PROJECT_DIR", ".")).resolve()
relay_config = project_dir / ".agentclaw" / "relay.json"
base_url = os.getenv("AGENTCLAW_INTERNAL_URL", "").rstrip("/")
if not base_url and relay_config.exists():
base_url = json.loads(relay_config.read_text(encoding="utf-8"))["internal_url"].rstrip("/")
url = f"{base_url}/_internal/api/workflow/run"
错误响应
{"error": "错误描述", "code": "ERROR_CODE"}
HTTP 状态码: 400 参数错误, 401 未认证, 404 未找到, 500 内部错误
按需读取参考文档
references/workflow.md — 工作流执行与对话
- 列出所有可用工作流
- 执行工作流（blocking 同步 / streaming SSE 流）
- HumanNode 交互续传（等待人工输入后继续）
- 确认危险操作
- SSE 流模式事件序列
- 上下文压缩 / 截断（编辑重试）
- 对话 CRUD（创建、列出、获取详情含消息、更新标题、删除）
- 消息反馈（like / dislike）
- 文件上传 / 下载（multipart 上传、按 ID 下载、Token 临时链接）
What ships with it
7 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.
- 2mo ago First seen · 124 lines · 57 tokens per session scan A a64c2e295977
agentclaw_api is a skill published in the GitHub repository Negai-ai/AgentClaw (315 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,557 once invoked, about $0.0002 per session on Opus 5.5. 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.
agentclaw_api compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentclaw_apiNegai-ai/AgentClaw | Skill | 315 | 5mo ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |