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 instructions/reorx/httpstat/agents-mdgit clone --depth 1 https://github.com/reorx/httpstatWhat 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 | $0.01193 | $0.01193 |
| Opus 5 | $0.00596 | $0.00596 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
httpstat AGENTS.md 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `skills/httpstat/SKILL.md`:已完成初版诊断 skill,覆盖自动安装、瓶颈识别、SLO 阈值、curl 转换。 How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
httpstat 项目规划
1) 项目现状
- 单文件 CLI (
httpstat.py, ~370 行),Python >=3.9,版本 2.0.0。 - 打包完全由
pyproject.toml驱动(setuptools),setup.py已删除。 - 构建/发布使用
uv build/uv publish。 - 测试为
httpstat_test.sh(端到端 shell 脚本,依赖外网站点)。
已完成的现代化工作
- 去除所有 Python 2 兼容代码,shebang 改为
#!/usr/bin/env python。 - 全量 f-string,新式 class 语法,类型标注(
Env类 overload、NoReturn)。 - 严格布尔解析
parse_bool(),替代'true' in value.lower()。 - 临时文件
try/finally统一清理,不再泄漏。 quit()重命名为_exit()并标注NoReturn。
2) 剩余技术债
A. 测试可靠性不足(高优先级)
- 仅有 shell E2E,强依赖公网与第三方站点行为,CI/本地结果不稳定。
- 缺少单元测试,核心逻辑(指标换算、区间计算、
parse_bool)没有稳定回归保障。
B. Agent 适配能力不足(中高优先级)
- 当前 JSON 输出缺少 schema version、状态码语义、错误结构、上下文元数据。
- 缺少"可机器判断"的 SLO/阈值能力(例如总耗时超阈值即非 0 退出)。
- 输出模式较少,无法直接覆盖 Agent 常见流水线(JSONL、紧凑 JSON、纯错误对象)。
3) 下一阶段推进方案
Phase 1:结构化输出 + SLO(本轮实施)
输出格式
- 新增
--format(-f):pretty | json | jsonl(默认pretty,兼容现有行为)。 HTTPSTAT_METRICS_ONLY环境变量保留兼容,等价于--format json。- JSON v1 schema(最小集,后续通过 schema_version 扩展):
{ "schema_version": 1, "url": "...", "ok": true, "exit_code": 0, "response": { "status_line": "HTTP/2 200", "status_code": 200, "remote_ip": "...", "remote_port": "...", "headers": {"Content-Type": "application/json", "Server": "nginx", "...": "..."} }, "timings_ms": { "dns": 5, "connect": 10, "tls": 15, "server": 50, "transfer": 20, "total": 100, "namelookup": 5, "initial_connect": 15, "pretransfer": 30, "starttransfer": 80 }, "speed": { "download_kbs": 1234.5, "upload_kbs": 0.0 }, "slo": { "pass": true, "violations": [] } }
SLO 阈值
- 单一参数
--slo key=value,...,例如--slo total=500,connect=100,ttfb=200。 - 支持的 key:
total、connect、ttfb(starttransfer)、dns、tls。 - 超阈值时退出码为
4,JSON 中slo.pass=false,slo.violations列出超标项。 - pretty 模式下在输出末尾用红色标注超标指标。
颜色控制
- 遵循
NO_COLOR环境变量(https://no-color.org)。设置后禁用所有 ANSI 颜色。 - 不新增
--no-color命令行参数,减少 flag 膨胀。
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 · 99 lines · 1,193 tokens per session scan A 92d29ac94d34
httpstat AGENTS.md is an instructions file published in the GitHub repository reorx/httpstat (6,218 stars, last pushed 4mo ago), licensed MIT. It adds 1,193 tokens to every session, about $0.0060 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 instructions, from other repositories
pygraphistry AGENTS.md
Instructions for graphistry/pygraphistry, covering agents.md, skill locations, platform path conventions, canonical -> tool-expected path and claude path to shared skills.
pygraphistry CLAUDE.md
Instructions for graphistry/pygraphistry: See AGENTS.md for repository AI guidance.
madrix-mcp AGENTS.md
Instructions for drohi-r/madrix-mcp, covering agents.md, project, core rules, key commands and key paths.
deepagents AGENTS.md
Instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
pygwalker CLAUDE.md
Instructions for Kanaries/pygwalker, covering claude.md and tl;dr for a coding agent.
python-cheatsheet copilot-instructions.md
Copilot instructions for labex-labs/python-cheatsheet, covering python cheatsheet - ai coding assistant instructions, project overview, architecture & key patterns, content structure and routing & layout system.