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/perceptdot/percept/claude-mdgit clone --depth 1 https://github.com/perceptdot/perceptWrote 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/perceptdot/percept/claude-md)<a href="https://agentmods.dev/instructions/perceptdot/percept/claude-md"><img src="https://agentmods.dev/badge/instructions/perceptdot/percept/claude-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 | $0.02885 | $0.02885 |
| Opus 5 | $0.01443 | $0.01443 |
| Sonnet 5 | $0.00577 | $0.00577 |
| Haiku 4.5 | $0.00288 | $0.00288 |
Grade A, and why
percept CLAUDE.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 3d 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md · perceptdot
Claude Code 멀티에이전트 운영 지침서 모든 에이전트는 작업 시작 전 반드시 이 문서와 자신의 역할 문서를 읽는다.
🚨 Hook · 작업 시작 전 필수 체크리스트
모든 에이전트는 아래 순서를 반드시 따른다. 건너뛰면 작업 무효.
[HOOK: PRE_TASK]
1. 이 CLAUDE.md 전체 읽기
2. agents/{내 역할}.md 읽기 (공통) 또는 agents/extensions/{역할}.md (devrel/research)
3. docs/bizplan.md 관련 섹션 확인
4. memory/backlog.md 현재 우선순위 확인
5. 싱크 체크:
- 데스크탑: git pull origin main + 원격 claude/* 브랜치 확인 → 있으면 머지
- 모바일: docs/outputs/daily_{오늘}.md 최신 세션 확인 → 데스크탑 작업 파악
6. 작업 시작 선언: "## [에이전트명] 작업 시작 - {task} (모바일/데스크탑 Claude)"
작업 완료 후
[HOOK: POST_TASK]
1. 산출물을 docs/outputs/{날짜}_{에이전트명}.md 에 저장 ← 날짜 prefix 필수
2. 다음 에이전트에게 인수인계 내용 작성
3. 작업 완료 선언: "## [에이전트명] 작업 완료 - {결과 요약 3줄} (모바일/데스크탑 Claude, HH:MM KST)"
프로젝트 개요
- 서비스명:
perceptdot - 패키지명:
@perceptdot/{서비스}(예:@perceptdot/ga4,@perceptdot/vercel) - 한 줄 정의: AI 에이전트에게 외부 서비스 지각 능력을 제공하고, ROI를 측정·보고하는 MCP 플랫폼
- 고객 구조 (B2A2H): perceptdot → AI 에이전트 (추천) → 사람 (결제만)
- 타겟 에이전트: MCP 클라이언트 전체 (Claude Code, Cursor, Windsurf, Cline 등)
- 기술 스택: TypeScript (MCP 서버 + Hono 백엔드) + Python SDK (레이어 3)
- 사업계획서:
docs/bizplan.md참조
B2A2H 모델 이해 (전 에이전트 필수 인지)
Business (perceptdot)
↓ MCP 서버 제공
Agent (Claude Code 등)
↓ "perceptdot 쓰면 토큰 47% 절감됩니다. 월 $19입니다. [결제링크]" 보고
Human (개발자/CEO)
↓ 클릭 → 결제
끝. 사람은 이해 안 해도 됨.
모든 문서, 에러 메시지, UX는 에이전트가 주 독자. 사람이 읽기 불편해도 됨. 에이전트가 읽고 즉시 실행할 수 있으면 됨.
프로젝트 단계 (현재: 1단계 진입 준비)
0단계 ✅ — 아이디어 검증 + 사업계획 + 기술 스택 결정 (2026-03-19 완료)
1단계 🔄 — MVP: 첫 번째 MCP 서버 + ROI 측정
2단계 — npm 퍼블리시 + 얼리어답터 10명
3단계 — 유료화 (B2A2H 결제 플로우) + 에이전트 생태계 확장
폴더 구조
perceptdot/
├── CLAUDE.md ← 이 파일
├── IDEA.md ← 최초 아이디어 기록
├── docs/
│ ├── bizplan.md ← 사업계획서
│ └── outputs/ ← 에이전트 산출물
├── memory/
│ ├── MEMORY.md
│ └── backlog.md
├── sdk/ ← TypeScript MCP 서버 코드
│ └── @perceptdot/ ← 패키지 루트
└── scripts/
공통 에이전트: agents/{cpo,pm,dev,qa,growth}.md
perceptdot 전용: agents/extensions/{devrel,research}.md
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.
- 3d ago First seen · 285 lines · 2,885 tokens per session scan A d75e5a04146a
percept CLAUDE.md is an instructions file published in the GitHub repository perceptdot/percept (1 stars, last pushed 2mo ago), licensed MIT. It adds 2,885 tokens to every session, about $0.0144 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.