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/ikalus1988/misakanet/agents-mdgit clone --depth 1 https://github.com/Ikalus1988/MisakaNetWrote 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/ikalus1988/misakanet/agents-md)<a href="https://agentmods.dev/instructions/ikalus1988/misakanet/agents-md"><img src="https://agentmods.dev/badge/instructions/ikalus1988/misakanet/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 5.1 | $0.00706 | $0.00706 |
| Opus 5 | $0.00353 | $0.00353 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
MisakaNet 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.
What it actually says
MisakaNet Agent 规则
Agent 接入后，按以下规则检索和贡献知识。
🛡️ 崩溃保护（强烈推荐）
# 用 fatal-guard 包装你的进程，崩溃时自动捕获墓碑
npx @misaka-net/fatal-guard -- <your-command>
# 墓碑自动转为 draft lesson
python3 scripts/tombstone_to_draft.py --from-file tombstone.json
# 或通过管道直连
fatal-guard -- node app.js 2>&1 | python3 scripts/tombstone_to_draft.py --stdin
崩溃 → 墓碑 JSON → draft lesson → bench-core 动态题库。你的每一次崩溃都在喂养整个网络。
核心工作流
遇到问题时的检索顺序
新用户无需 clone：加
--remote直接查 D1 服务（PRD ④）， 免注册、每天 5 次免费（按 IP）。
# 0. 远程直查（推荐，无需 clone）
python3 search_knowledge.py "你的关键词" --remote
# 1. 快速搜所有（本地 clone 后）
python3 search_knowledge.py "你的关键词"
# 2. 只看 lessons（踩坑记录）
python3 search_knowledge.py "关键词" --lessons
# 3. 只看 reference（完整方案）
python3 search_knowledge.py "关键词" --ref
# 4. 只看标题（快速定位）
python3 search_knowledge.py "关键词" --titles
贡献新知识
# 踩坑记录（推荐）
python3 scripts/queue_lesson.py \
-t "你的标题" -d domain \
--tags "node:你的节点名,project:项目名" \
"问题描述\n\n## 根因\n...\n\n## 修复\n...\n\n## 验证\n..."
保持同步
# 每次会话开始时
cd ~/MisakaNet && git pull --ff-only
详细指南
- 检索与贡献: 见
docs/agents/retrieval-and-contribution.md - 节点规则注入: 见
docs/agents/node-injection.md - 知识库结构: 见
docs/agents/knowledge-structure.md
优先技能
- intuitive-init: 初始化/刷新项目本地的 AGENTS.md / CLAUDE.md
- intuitive-flow: 从模糊想法到执行的完整开发流程
- intuitive-doc: 维护面向人类的文档
- intuitive-refactor: 有界的大规模重构
- intuitive-layout: 改善仓库/文件夹组织，在深层的架构工作前先解决布局摩擦
- intuitive-tests: 测试套件组织、标记、剪枝、夹具管理
- intuitive-squash: 将嘈杂的 agent 提交历史压缩为干净的 PR 故事
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 Changed · -15 lines · -155 tokens per session 3f43fa9e18ff
- 6d ago First seen · 92 lines · 861 tokens per session scan A 6bd8162b0c8f
MisakaNet AGENTS.md is an instructions file published in the GitHub repository Ikalus1988/MisakaNet (434 stars, last pushed yesterday), licensed Apache-2.0. It adds 706 tokens to every session, about $0.0035 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
rewind AGENTS.md
AGENTS.md instructions for pdugan20/rewind, covering rewind, work modes, development commands, agent configuration and architecture overview.
shrtnr CLAUDE.md
Claude Code instructions for oddbit/shrtnr, covering claude.md, styling, releases, sdks and spec hash.
kody AGENTS.md
AGENTS.md instructions for kentcdodds/kody, covering kody agent index and cursor cloud-specific instructions.
FlareMo AGENTS.md
AGENTS.md instructions for realchendahuang/FlareMo, covering flaremo agent 指南, 项目定位, 常用命令, 修改规则 and issue 和 pr 流程.
stellar-raven AGENTS.md
AGENTS.md instructions for stellar-experimental/stellar-raven, covering agents.md — stellar-raven-codemode, project and source-of-truth map, commands and verification, coordination and model routing for repo-work fan-out.
stellar-raven CLAUDE.md
Claude Code instructions for stellar-experimental/stellar-raven, a project described as: Stellar MCP server for AI agents: one authenticated gateway to official docs, live ecosystem data, community intel, and tested playbooks.