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/foru17/neko-master/agents-mdgit clone --depth 1 https://github.com/foru17/neko-masterWrote 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/foru17/neko-master/agents-md)<a href="https://agentmods.dev/instructions/foru17/neko-master/agents-md"><img src="https://agentmods.dev/badge/instructions/foru17/neko-master/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 | $0.02948 | $0.02948 |
| Opus 5 | $0.01474 | $0.01474 |
| Sonnet 5 | $0.00590 | $0.00590 |
| Haiku 4.5 | $0.00295 | $0.00295 |
Grade A, and why
neko-master 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 4d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working in this monorepo. This file is the single source of truth for agent guidance — CLAUDE.md and .github/copilot-instructions.md are thin pointers to it.
Scope and Priorities
- Follow this file for repo-specific workflows and conventions.
- Follow direct user instructions over this file when they conflict.
- Keep changes minimal, targeted, and consistent with existing code.
Skills (task-specific workflow guides)
Reusable process checklists live in .claude/skills/*/SKILL.md (plain Markdown — usable by any tool; Claude Code loads them automatically). Consult the matching one BEFORE starting these task types:
| Skill | When to use |
|---|---|
verify-changes |
After any edit — minimal check set per touched area |
add-stats-dimension |
Any schema / stats-table / write-path change (several registries must change together) |
release |
Version bumps, CHANGELOG, tagging, CI verification |
ui-conventions |
Any UI change — i18n, dark mode, three-state views |
db-conventions |
Queries, repositories, ClickHouse topology, debugging data drift |
agent-probe-dev |
Anything under apps/agent (Go probe) |
Repository Overview
- Package manager:
pnpm(workspace monorepo). - Task runner:
turboat repo root. - Main apps:
apps/web: Next.js 16 + React 19 frontend.apps/collector: Fastify + WebSocket + SQLite backend service.apps/agent: Go probe deployed on routers/servers (reports to the collector over HTTP).
- Shared package:
packages/shared: shared TypeScript types and utility functions.
Project Map (key files)
apps/collector/src/
database/schema.ts # ALL table/index DDL (single source of truth)
database/repositories/
traffic-writer.repository.ts # THE traffic write path (batchUpdateTrafficStats)
base.repository.ts # time keys, range routing (resolveFactTable), chain parsing
rule.repository.ts # rule stats + chain-flow DAG queries
backend.repository.ts # backend CRUD + deleteBackendData table list
config.repository.ts # retention deletes, app_config
shared/utils/rule-name.ts # buildRuleName — the rule naming contract
modules/collector/ # gateway WS clients + BatchBuffer (30s flush)
modules/realtime/realtime.store.ts # in-memory deltas between flushes
modules/websocket/websocket.server.ts # web-client WS: subscriptions, broadcast, backpressure
modules/stats/stats.service.ts # SQLite/ClickHouse read routing (*WithRouting)
modules/clickhouse/ # CH writer/reader/config (parity with SQLite reads)
modules/app/app.ts # Fastify composition root + agent ingest endpoints
apps/web/
lib/api.ts, lib/websocket.ts # HTTP client + stats WS hook (backendId-tagged pushes)
lib/stats-query-keys.ts # centralized React Query keys
messages/{zh,en}.json # i18n — every key in BOTH files
components/features/ # domain components (rules/, countries/, backend/, stats/)
app/[locale]/dashboard/ # main dashboard route
apps/agent/
internal/agent/runner.go # main loop, retry/idempotency
nekoagent # POSIX-sh service manager (install/upgrade/systemd/procd)
docs/
architecture(.en).md # system architecture
agent/ # probe docs (user-facing)
dev/ # internal analysis reports (not authoritative)
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.
- 4d ago First seen · 236 lines · 2,948 tokens per session scan A 49ace1a5734b
neko-master AGENTS.md is an instructions file published in the GitHub repository foru17/neko-master (3,861 stars, last pushed 1mo ago), licensed MIT. It adds 2,948 tokens to every session, about $0.0147 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
yaml-proxy-editor AGENTS.md
AGENTS.md instructions for NextWeb4/yaml-proxy-editor, covering agents.md, 1. project structure, 2. run commands, 3. test commands and 4. build commands.
Vibe-Research AGENTS.md
Instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).
pygwalker CLAUDE.md
Instructions for Kanaries/pygwalker, covering claude.md and tl;dr for a coding agent.
worldmonitor AGENTS.md
AGENTS.md instructions for koala73/worldmonitor, covering agents.md, task mode and authority, start here, surface routing and architecture invariants.
vizro copilot-instructions.md
Copilot instructions for mckinsey/vizro, covering github copilot instructions for vizro, pull requests from bots and automated tooling and everything else.
metabase copilot-instructions.md
Copilot instructions for metabase/metabase, covering metabase developer assistant instructions, code review standards, security critical issues, performance red flags and code quality essentials.