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/talesofai/okp/agents-mdgit clone --depth 1 https://github.com/talesofai/okpWrote 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/instructions/talesofai/okp/agents-md)<a href="https://agentmods.dev/instructions/talesofai/okp/agents-md"><img src="https://agentmods.dev/badge/instructions/talesofai/okp/agents-md.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 | $0.01386 | $0.01386 |
| Opus 5 | $0.00693 | $0.00693 |
| Sonnet 5 | $0.00277 | $0.00277 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
okp AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Project Conventions for okp
Overview
Open Knowledge Protocol (okp) — open structured knowledge for people and agents. PostgreSQL-backed storage with API/CLI/Skills access surfaces.
Tech Stack
- Backend: Go 1.26+, chi v5 (router), GORM v2 (ORM), pgx (PG driver)
- Database: PostgreSQL — 唯一存储层，无 Redis/缓存依赖
- CLI: cobra (命令行框架)，与 API 共享 service 层
- Skills: 纯 Markdown 指令文件，同构于 lark-* skill 模式
Architecture
cmd/api/ — HTTP API 入口
cmd/cli/ — CLI 入口（开发者工具 + 脚本集成）
internal/
config/ — 环境变量配置
model/ — GORM 数据模型（Concept, Link, Revision）
store/ — 数据库初始化和连接管理
handler/ — HTTP handlers（6 端点 + health + domains list）
service/ — 业务逻辑（CRUD, search, lint, export）
middleware/ — HTTP 中间件（auth token, logging, recovery）
skills/
okp-import/ — 导入 skill（面向领域 owner 的 agent）
references/ — 各 type 的 concept 模板和 golden examples
okp-search/ — 搜索 skill（面向消费 agent）
embed.go — go:embed shim，供 CLI `okp skills install` 内嵌安装
API 端点
PUT /api/v1/concepts/* — upsert（L1 硬门禁在此校验；concept ID 含 /，用 catch-all 通配）
DELETE /api/v1/concepts/* — 删除 concept + links + revisions
POST /api/v1/concepts:batch — 批量 upsert
GET /api/v1/concepts — list/search（domain/type/tag/status/q）
GET /api/v1/concepts/* — 单取
GET /api/v1/links/* — 出链 + 反向引用（links 拆为独立顶层资源）
PUT /api/v1/links/* — 替换概念的出链
GET /api/v1/domains/{domain}/export — OKF bundle 导出（NDJSON 概念流，由客户端本地渲染文件树）
GET /api/v1/domains/{domain}/activity — 日粒度创建、更新和成功知识读取请求（默认 30 天，最多 365 天）
GET /api/v1/domains — 领域清单（concept 数及聚合 created_at/updated_at）
PUT /api/v1/domains/{domain} — 创建/更新 README、schema、visibility
DELETE /api/v1/domains/{domain} — 级联删除 domain 全部数据
GET /api/v1/health — 健康检查
路由设计：concept ID 用 OKF 原生 / 分隔符。Go net/http 和 chi 的 {id} 无法跨 / 段捕获，故 concepts 用 catch-all /*；chi 的 * 必须在末尾（/concepts/*/links 会 panic），因此 links 拆为独立顶层资源 /links/*。好处：ID 保持 OKF 原生格式，export/import 与 OKF bundle 1:1 映射，body cross-reference 可直接解析。
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 · 97 lines · 1,386 tokens per session scan A 5f0dbab5f5e1
okp AGENTS.md is an instructions file published in the GitHub repository talesofai/okp (5 stars, last pushed 10d ago), licensed MIT. It adds 1,386 tokens to every session, about $0.0069 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 2026-08-31.
Other instructions, from other repositories
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
obsidian-llm-wiki AGENTS.md
AGENTS.md instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.
docsmint AGENTS.md
AGENTS.md instructions for HiAi-gg/docsmint, covering docsmint — agents.md, cheat-sheet — conventions, project documents, core and project-specific.
SoDam-WikiMate AGENTS.md
AGENTS.md instructions for sodam-ai/SoDam-WikiMate, covering wikimate 작업 규칙 (크로스툴 — claude code · codex · gemini 공용), 문체, 자동 동작 (자연어 트리거 — 강제 호출 불필요), 접근 규칙 (자동 감지 — 특정 도구에 한정하지 않음) and obsidian 규칙.
ariadne AGENTS.md
Instructions for pariyar07/ariadne, covering ariadne — agent instructions, what this repo contains, how skills are structured, routing and rules.
soia-open-skills AGENTS.md
AGENTS.md instructions for soia-team/soia-open-skills, covering agents.md - soia-open-skills, repository purpose, safety rules, validation and git workflow（本仓特有：默认分支是 main）.