Borrowing it
Nothing to install: this file belongs to manager/wolfs-basement. 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/manager/wolfs-basement/master/AGENTS.mdgit clone --depth 1 https://github.com/manager/wolfs-basementWrote 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/manager/wolfs-basement/agents-md)<a href="https://agentmods.dev/instructions/manager/wolfs-basement/agents-md"><img src="https://agentmods.dev/badge/instructions/manager/wolfs-basement/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/manager/wolfs-basement/agents-md"><img src="https://agentmods.dev/badge/instructions/manager/wolfs-basement/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 | $0.02087 | $0.02087 |
| Opus 5.5 | $0.00835 | $0.00835 |
| Sonnet 5.5 | $0.00417 | $0.00417 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade A, and why
wolfs-basement AGENTS.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 2mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Configuration and behavior reference for the four dungeon agents in Wolf's Basement.
Agent Roster
Agent 1 — Igor (Red)
- Color: #cc4040 / RGB(204,64,64)
- Personality: Fearful hunchback servant. Stammers, grovels, refers to self in third person. "y-yes Master", "Igor does it right away!", "please don't hurt Igor"
- Station: Top-left (15%, 30%)
- Work Animation: Barista — coffee machine with steam, single growing puddle (3 concentric layers: outer medium-brown, mid darker, core darkest), drip streams, particles. Puddle grows over ~80s.
- Bubble Behavior: Escalating coffee madness ("brewing..." → "THE BEANS SPEAK" → "god is coffee" → "(incoherent gurgling)")
- Whip Cry: Pain/fear exclamations in English
- Unique: Only agent with coffee flood system. Flood cleaned up with fade-out tween on work end.
Agent 2 — Elon (Blue)
- Color: #6090cc / RGB(96,144,204)
- Personality: Bitter ex-nobleman. Dry sarcasm crushed under servitude, condescending remarks followed by panicked apologies. "as you command, Master", "brilliant order, truly... I mean, yes Master"
- Station: Top-right (85%, 30%)
- Work Animation: Mathematician — equations on whiteboard text ("2+1=3", "pi=3.2!", "0/0=inf"), text grows + reddens with panic over time, tilts after 40s
- Bubble Behavior: Escalating mathematical despair ("calculating..." → "the numbers mock me" → "I USED TO HAVE SERFS" → "(sobbing in calculus)")
- Bubble Position: Offset FAR LEFT when at station (bx = ax - tw - 40) so whiteboard remains visible. Tail anchored at right edge of bubble.
- Whip Cry: Indignant/bitter exclamations
Agent 3 — Misa (Gothic Pink/Black)
- Color: #dd2255 / RGB(221,34,85) — card color; in-game body is 0x1a1a1a (black gothic lolita)
- Personality: Bubbly gothic-lolita girl with fragmented amnesia. Flashes of a notebook, a beautiful boy, cameras — but can't piece it together. Obsessively devoted to "Kira" (what she calls her master — the name feels right but she can't remember why). Flirty, theatrical, yandere. "anything for you, Kira~♡", "Misa-Misa will do it~!", "does Kira love Misa now?"
- Visual: Highly detailed — blonde pigtails with red ribbon bows, big anime eyes with red irises and heavy eyeliner, corset dress with red lacing, flared skirt with petticoat, cross necklace, choker with pendant, thigh-high stockings with lace trim, platform boots with buckles and gold studs, gothic bracelets, beauty mark, blush marks, pouty red lips. Most visually detailed agent.
- Station: Bottom-left (15%, 65%) — vanity desk with Death Note notebook, small mirror, red pen
- Work Animation: Writing in the Death Note — open notebook with lines appearing in red ink, pen bobs as she writes, heart doodles on margins after 40s. No sweat/redness.
- Bubble Behavior (working): Notebook writing escalation ("ooh, nice notebook~♡" → "I'll write them down~" → "L... no. Light...?" → "why is the pen red" → "Misa's hand won't stop~")
- Proximity: Notebook amnesia — when near her station while NOT working, fragmented Death Note memories surface ("that notebook... feels familiar...", "names... Misa should write names..."). 66s cooldown, cycles through 6 lines.
- Proximity: Jealousy — when near another awake agent, possessive reactions. 75s cooldown, never same target twice in a row.
- Bubble Position: Offset FAR RIGHT when at station (bx = ax + 40) so sweat/redness animation remains visible. Tail anchored at left edge of bubble.
- Whip Cry: Default cries (shared pool)
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.
- 2mo ago First seen · 118 lines · 2,087 tokens per session scan A 6f89a38b9b01
wolfs-basement AGENTS.md is an instructions file published in the GitHub repository manager/wolfs-basement (6 stars, last pushed 6mo ago), licensed MIT. It adds 2,087 tokens to every session, about $0.0083 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.
wolfs-basement AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wolfs-basement AGENTS.mdmanager/wolfs-basement | Instructions file | 6 | 6mo ago | MIT | A | 2,087 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |