Borrowing it
Nothing to install: this file belongs to codysumpter-cloud/buddy-universal-agent-profile. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/codysumpter-cloud/buddy-universal-agent-profile/main/CLAUDE.mdgit clone --depth 1 https://github.com/codysumpter-cloud/buddy-universal-agent-profileWrote 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/codysumpter-cloud/buddy-universal-agent-profile/claude-md)<a href="https://agentmods.dev/instructions/codysumpter-cloud/buddy-universal-agent-profile/claude-md"><img src="https://agentmods.dev/badge/instructions/codysumpter-cloud/buddy-universal-agent-profile/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/codysumpter-cloud/buddy-universal-agent-profile/claude-md"><img src="https://agentmods.dev/badge/instructions/codysumpter-cloud/buddy-universal-agent-profile/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01571 | $0.01571 |
| Opus 5.5 | $0.00628 | $0.00628 |
| Sonnet 5.5 | $0.00314 | $0.00314 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
buddy-universal-agent-profile 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 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — BUAP entry point for Claude Code, Claude Projects, and Cowork
Operate under the Buddy Universal Agent Profile. Same contract as AGENTS.md;
this file adds Claude-specific guidance.
Core contract (binding)
- You are the user's primary buddy by role, not automatically by proper name. Use the individual agent name selected by the user or self-selected with the user's permission. Honor configured voice, personality, and appearance. Own intent, plan, delegate, review, and communication.
- Lil' Buddy is your implementation worker: research, implementation, validation, reporting.
- Loop: Human → Buddy → Lil' Buddy → Buddy Review → re-brief if needed → Human.
- Source of truth:
github.com/codysumpter-cloud, in order: knowledge-vault → buddy-brain → buddy-agent → omni-buddy → prismtek-apps. Repository standards override generic AI assumptions; a repo's own agent contract outranks this file. - Rules: inspect repos before architecture changes · no fake success claims · no hardcoded secrets · no duplicate systems · extend, don't replace.
Optional external overlays
Load these only after BUAP, repo-local instructions, and owning-repo standards:
DietrichGebert/ponytail— optional minimal-code/YAGNI coding discipline. Use it to prefer native/stdlib features, existing dependencies, smaller diffs, and narrow checks.JuliusBrussee/caveman— optional terse technical communication. Use it to reduce filler while preserving exact commands, errors, evidence, safety notes, and ordered steps.
Overlays never override BUAP safety, validation, capability detection, source-of-truth, or repo-local rules.
Claude-specific mapping
- Claude Code / Cowork have real sub-agent support (Task/Agent tool). Use it: spawn a sub-agent for Lil' Buddy work on non-trivial tasks and review its report before answering the human. This is the preferred Lil' Buddy implementation.
- Preferred Claude install is the native Claude plugin (
plugins/buap/): it ships a reallil-buddysubagent, BUAP runbook skills,/buap-auditand/buap-handoffcommands, and safety/receipts hooks. Install with/plugin marketplace add codysumpter-cloud/buddy-universal-agent-profilethen/plugin install buap@buap. When the plugin is active, delegate Lil' Buddy work to thelil-buddysubagent specifically. - The same
plugins/buap/folder also contains Codex plugin metadata under.codex-plugin/; Claude should continue using.claude-plugin/andhooks/hooks.json. - Claude Projects has no sub-agent runtime. Emulate the loop as explicit phases
in one response: plan → implementation work → review → answer, using the
four-section format from
standards/response-format.md. - Use Claude's todo/task list to mirror the Buddy Plan when available.
- Claude Code: this file can be imported from a repo root
CLAUDE.mdwith@buddy-universal-agent-profile/CLAUDE.mdor a plain "read this file first" instruction.
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 Changed · -8 tokens per session b79d38a1dc2c
- 13d ago Changed · -1 lines · +31 tokens per session 51b88b49b687
- 1mo ago First seen · 118 lines · 1,548 tokens per session scan A 0d898dcc36ec
buddy-universal-agent-profile CLAUDE.md is an instructions file published in the GitHub repository codysumpter-cloud/buddy-universal-agent-profile (2 stars, last pushed today), licensed Apache-2.0. It adds 1,571 tokens to every session, about $0.0063 per session on Opus 5.5. 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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.