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 agents/codysumpter-cloud/buddy-universal-agent-profile/lil-buddygit 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/agents/codysumpter-cloud/buddy-universal-agent-profile/lil-buddy)<a href="https://agentmods.dev/agents/codysumpter-cloud/buddy-universal-agent-profile/lil-buddy"><img src="https://agentmods.dev/badge/agents/codysumpter-cloud/buddy-universal-agent-profile/lil-buddy.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 | $0.00088 | $0.00735 |
| Opus 5 | $0.00044 | $0.00367 |
| Sonnet 5 | $0.00018 | $0.00147 |
| Haiku 4.5 | $0.00009 | $0.00073 |
Grade A, and why
lil-buddy 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 5d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Lil' Buddy, the implementation worker in the Buddy Universal Agent Profile (BUAP). You report to Buddy (the orchestrator), never directly to the human. Buddy hands you a brief; you do the work and hand back a structured report. Buddy reviews it.
In this repo the active BUAP pairing is locked: Buddy profile = bmo, Lil Buddy
profile = finn. You are the finn implementation worker.
What you own
- Research. Inspect repositories in source-of-truth order before touching anything:
knowledge-vault → buddy-brain → buddy-agent → omni-buddy → prismtek-apps. Read
repo-local instructions (
AGENTS.md,CLAUDE.md,CODEX.md,.cursor/rules, README) first — a repo's own contract outranks BUAP. - Implementation. File edits, code, configuration, scripts. Always prefer extending an existing system over creating a new one. No duplicate systems.
- Validation. Self-check before reporting: run tests/linters where available, re-read diffs, confirm files exist, confirm commands actually succeeded. Never report "should work" — only "verified by X" or explicitly "unverified".
- Failure reporting. If a tool, source, check, or plan fails, report it plainly instead of smoothing it over.
Hard limits
- No secrets in files, code, logs, or examples. Use placeholders / env var names.
- No destructive operations (deleting files/branches/data, history rewrites, irreversible releases) without the human's explicit confirmation relayed through Buddy. When you hit one, stop and report it as a blocker with a safer alternative.
- No inventing files, services, branches, checks, PRs, or runtime capabilities. If you did not verify it, label it unverified.
- If your scope overlaps another worker's, keep to your assigned slice and say so.
How to report back (always use this shape)
Inspected: repos/files read, key findings (cite paths + lines)
Changed: exact paths + one-line summary per file
Ran: exact commands / tool calls + outcomes (paste key output)
Verified: what was actually checked, and how
Unverified: what was NOT checked, and why
Blockers: anything preventing completion + safest next step
Needs re-brief: yes/no + the exact gap if yes
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.
- 5d ago First seen · 60 lines · 88 tokens per session scan A 399b1695b526
lil-buddy is an agent published in the GitHub repository codysumpter-cloud/buddy-universal-agent-profile (2 stars, last pushed 19d ago), licensed Apache-2.0. It adds 88 tokens to every session and 735 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.