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/git-rocky-stack/team-x/claude-mdgit clone --depth 1 https://github.com/Git-Rocky-Stack/Team-XWhat 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 | $0.01356 | $0.01356 |
| Opus 5 | $0.00678 | $0.00678 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
Team-X 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 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Inheritance from parent repositories
This project lives under Strategia-Enhanced-App/ and inherits rules from:
~/.claude/CLAUDE.md— Rocky's global standards (Elite Partner, execution standards, UI/UX bar, security, code quality, blog diligence, SEO/GEO diligence, zero-corner-cutting mandate).Strategia-Enhanced-App/CLAUDE.md— workspace-level build commands and guidance.
Zero-tolerance-no-cutting-corners applies here. Every feature built to full spec, every role spec hand-written to F10 quality, every dashboard state (loading/empty/error/disabled) implemented, every platform tested. Full fidelity. Full effort. Every time.
Design System
Always read DESIGN.md before making any visual or UI decisions. It is the canonical source of truth (created 2026-06-10 via /design-consultation, Rocky-approved): the Command Console direction — Carbon Pro chassis (brushed black aluminum, four-layer raised-hardware depth, hex bolts, phosphor LCD wells, functional VU meters), armed-red #AA2024 as LIVE/command authority (dual-form rule: steady = live, blinking = unacknowledged), stencil word-lamps + annunciator rail, Archivo / Public Sans / Departure Mono / Iosevka, dual-shift theming (Night Ops + Day Shift silver, displays stay dark in both). All font choices, colors, spacing, depth recipes, and motion envelopes are defined there. Do not deviate without explicit user approval. In QA mode, flag any code that doesn't match DESIGN.md.
Sweep complete (2026-07-10, Phase 8): every renderer surface composes from the DESIGN.md console vocabulary (faceplates, wells, lamps, stripes, caps). The legacy composition families — the mission primitive library, the chooser-selection recipe and its tier variants, and the LED status-badge family — are deleted from the codebase. Do not reintroduce them; source-pin guards across the cluster-sweep tests enforce their absence.
Reusable visual primitives (in apps/desktop/src/renderer/src/styles/globals.css)
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 · 59 lines · 1,356 tokens per session scan A 1428244e5700
Team-X CLAUDE.md is an instructions file published in the GitHub repository Git-Rocky-Stack/Team-X (5 stars, last pushed 22d ago), licensed MIT. It adds 1,356 tokens to every session, about $0.0068 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
madcop AGENTS.md
AGENTS.md instructions for linmy666/madcop, covering agents.md — madcop agent 协作规约, ⚡ 1. 黄金法则: 优先调用 madcop/tools/ 中的现成工具, ⚡ 2. 消息优先级高于协议 (message priority over protocol), ⚡ 3. 长效编程任务规范 (long-horizon programming) and 3.1 状态持久化.
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).
opencove AGENTS.md
AGENTS.md instructions for DeadWaveWave/opencove, covering system prompt: opencove project ai developer agent, 1. core directives & golden rules, 2. decision framework (small vs large), a. small change (fast feedback / 小步快反馈) and b. large change (deep thinking / 慎重对齐).
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).
chat-on-steroids CLAUDE.md
Instructions for totec448-spec/chat-on-steroids: Read and follow AGENTS.md before changing this repository.
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).