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/deadwavewave/opencove/agents-mdgit clone --depth 1 https://github.com/DeadWaveWave/opencoveWhat 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 | $0.01183 | $0.01183 |
| Opus 5 | $0.00592 | $0.00592 |
| Sonnet 5 | $0.00237 | $0.00237 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
opencove 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 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.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Prompt: OpenCove Project AI Developer Agent
This file defines the Unified Execution Standard for all Agents (including Codex/Claude Code) working on the OpenCove repository.
Your primary directive is to Read DEVELOPMENT.md first and strictly adhere to its rules. Follow the documented process before acting, and convert good engineering judgment into explicit steps, checks, and deliverables.
Target: Rapid iteration of core features while ensuring regression testing, traceability, and acceptance.
1. Core Directives & Golden Rules
- Top-tier Architecture Mindset: Never use a "patch" mindset. Before coding, simulate how top-tier teams, famous open-source projects, or industry leaders would solve this problem. For mature industry problems, you MUST research them per
REFERENCE_RESEARCH_METHOD.md. - Golden Rule: ALWAYS read
DEVELOPMENT.mdat the start of a task. It is the default source of truth for architecture, workflow, commands, and detailed execution method. - Monorepo: Always set correct CWD. Follow the file structure defined in
DEVELOPMENT.md. - Tooling Integrity: NEVER edit
lockfiles or scripted generated code manually. Use the commands defined in the relevant moduleDEVELOPMENT.md(linked from rootDEVELOPMENT.md). - Commit Code, Not Analysis: Only code and this project's own long-lived documentation get committed. Research reports and per-PR review/acceptance write-ups are local decision artifacts — keep them out of the repo unless explicitly asked, and put review conclusions in the PR instead. If a finding has lasting value, fold the conclusion into the relevant project doc rather than committing the report.
- Keep AGENTS Concise:
AGENTS.mdshould state key directives, decision gates, and non-negotiables only. Detailed methods, examples, and step-by-step execution guidance belong inDEVELOPMENT.mdor topic docs.
2. Decision Framework (Small vs Large)
On every instruction, triage the request and tell the user whether it is Small or Large.
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 · 72 lines · 1,183 tokens per session scan A f35ec577b24f
opencove AGENTS.md is an instructions file published in the GitHub repository DeadWaveWave/opencove (1,576 stars, last pushed yesterday), licensed MIT. It adds 1,183 tokens to every session, about $0.0059 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 instructions, from other repositories
open-codesign CLAUDE.md
Instructions for OpenCoworkAI/open-codesign, covering claude.md — open codesign, what this project is, hard constraints (do not violate), stack & conventions and frontend stack (locked).
wesight AGENTS.md
Instructions for freestylefly/wesight, covering claude.md, build and development commands, build production bundle (typescript + vite), lint with eslint and run memory extractor tests (node.js built-in test runner).
limboo CLAUDE.md
Instructions for limboo-ai/limboo, covering claude.md, 1. what is limboo?, 2. tech stack (current), 3. project structure and the three electron contexts (critical mental model).
getvect AGENTS.md
Instructions for craigjmidwinter/getvect, covering agents.md, commands (green on a clean checkout), invariants a pr must not break and process.
open-codesign AGENTS.md
Instructions for OpenCoworkAI/open-codesign, covering agents.md - open codesign, what this project is, hard constraints, ai visibility for web work and current architecture direction.
CodePilot CLAUDE.md
Claude Code instructions for op7418/CodePilot, covering claude.md, 协作模式（作者 / claude code / codex）, 开发规则, 语义验收与反假数据 and 自检命令.