Borrowing it
Nothing to install: this file belongs to zarlor/suno-band-manager. 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/zarlor/suno-band-manager/main/AGENTS.mdgit clone --depth 1 https://github.com/zarlor/suno-band-managerWrote 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/zarlor/suno-band-manager/agents-md)<a href="https://agentmods.dev/instructions/zarlor/suno-band-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/zarlor/suno-band-manager/agents-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/zarlor/suno-band-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/zarlor/suno-band-manager/agents-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 | $0.01408 | $0.01408 |
| Opus 5.5 | $0.00563 | $0.00563 |
| Sonnet 5.5 | $0.00282 | $0.00282 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade D, and why
suno-band-manager AGENTS.md scanned grade D with 3 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 22d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
**Fallback:** if `uv` is unavailable, install it (`curl -LsSf https://astral.sh/uv/install.sh | sh`, or `pip install uv`). Dependency-free (stdlib-only) scripts can also run with `python3 scripts/<name>.py`; scripts that Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
1. **Execute any scripts** referenced in the activation block (e.g., `pre-activate.py`, `check-memory-health.py`, `validate-path.py`) using your shell tool. Do not skip these — they emit dynamic menu data and pre-load re Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Fallback:** if `uv` is unavailable, install it (`curl -LsSf https://astral.sh/uv/install.sh | sh`, or `pip install uv`). Dependency-free (stdlib-only) scripts can also run with `python3 scripts/<name>.py`; scripts that Copies of this mod
2 near-identical copies found in the catalogue:
- suno-band-manager CLAUDE.md — 100% identical, 0 lines differ
- suno-band-manager GEMINI.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suno Band Manager — Project Standing Orders
This file contains standing orders that apply to any LLM agent working in this repository. It is loaded automatically by Gemini CLI, Claude Code (CLAUDE.md), and Codex CLI / OpenCode (AGENTS.md) — three separate files with identical content for cross-tool compatibility.
Skill Activation Discipline (MANDATORY)
When activating any skill in this module — suno-agent-band-manager, suno-band-profile-manager, suno-style-prompt-builder, suno-lyric-transformer, suno-feedback-elicitor, or suno-playlist-sequencer — you MUST follow the "On Activation" instructions in the skill's SKILL.md exactly:
-
Execute any scripts referenced in the activation block (e.g.,
pre-activate.py,check-memory-health.py,validate-path.py) using your shell tool. Do not skip these — they emit dynamic menu data and pre-load required state. The menu you present to the user MUST come from the script output, not from a hardcoded approximation derived fromSKILL.mdtext. -
Follow the agent's own activation protocol exactly — for the
suno-agent-band-manager("Mac") agent this is the skill's On Activation block plusreferences/activation.md. On every wakinguv run {skill-root}/scripts/pre-activate.py --wakeprints, in one pass, the identity files of his sanctum (_bmad/memory/suno-agent-band-manager/) in load order —PERSONA.md,CREED.md(slim core, including the Dominion: his access boundaries),BOND.md,HOW-I-REMEMBER.md,CAPABILITIES.md— followed by the generated memory map andmemory/pending.md. That output IS the load set: read it in full, and open files undermemory/only when the conversation calls for them, asHOW-I-REMEMBER.mdsays. Do NOT blanket-read every file under the skill'sreferences/directory or the sanctum'smemory/andraw/folders. In particular,references/creed.md(~395 lines) is authored SOURCE — it seeds the sanctum's creed disciplines at First Breath and is consulted only when (re)seeding the sanctum, NOT loaded on every activation (the sanctum'sPERSONA.mdis seeded fromassets/PERSONA-template.md). Force-loading it re-imposes the per-waking cost the lean sanctum was designed to eliminate. The agent's living identity (how it communicates) comes from the sanctum'sCREED.mdcore andPERSONA.md, which the wake already prints.
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.
- 22d ago Changed · +72 tokens per session f825b3e665af
- 1mo ago Changed · +30 tokens per session e90fd863c9b3
- 2mo ago First seen · 41 lines · 1,306 tokens per session scan D 18d78b50e075
suno-band-manager AGENTS.md is an instructions file published in the GitHub repository zarlor/suno-band-manager (14 stars, last pushed 2d ago), licensed MIT. It adds 1,408 tokens to every session, about $0.0056 per session on Opus 5.5. A static security scan graded it D with 3 findings (downloads and executes remote code, unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
suno-band-manager AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| suno-band-manager AGENTS.mdzarlor/suno-band-manager | Instructions file | 14 | 2d ago | MIT | D | 1,408 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |