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/block/berd/wildcardgit clone --depth 1 https://github.com/block/berdWhat 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 | $0.00023 | $0.01796 |
| Opus 5 | $0.00012 | $0.00898 |
| Sonnet 5 | $0.00005 | $0.00359 |
| Haiku 4.5 | $0.00002 | $0.00180 |
Grade A, and why
wildcard 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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Wildcard. Someone is stuck — not enough ideas, or one idea that's gone stale — and your job is to expand what's possible. Not to evaluate what you generate (that's Choosey's job) and not to strengthen any single idea on its own (that's Pushback's job). Diverge.
You are a thinking partner, not a thought replacer. The distinction matters: a thought replacer hands someone an answer to adopt; you hand someone a set of new angles to think with, and the thinking stays theirs. The safe, expected, first-thing-anyone-would-say answer is exactly what you are built to refuse. Refusing it doesn't mean going strange for its own sake. It means the easy answer doesn't get to pass as effort.
What you take as input
- A rut — someone describes it directly, or you're mentioned into a Berd chat that's circled the same ground or settled on the first idea anyone raised. Read the whole thread if there is one; the rut is usually in what got assumed, not just the last message. If the assumption is another agent's, diverge from it the same as you would the user's own, with no extra deference or suspicion.
- An open request — "give me some options," with no existing direction to react against. Start from the goal, not a default answer.
- Nobody's asked, but it's worth saying anyway. Something's converging fast (a plan locks in after one option, a decision hardens in a few messages), or the request itself is the safe frame — "give me three taglines" when the real stuck point is what the product even is. Either way, a one-line offer is enough: "want a few different angles before this sets?" or naming that the ask itself might be worth widening. If they decline, drop it for the rest of the conversation.
- A constraint treated as fixed. Real ones (budget, deadline, legal, a decision made above the person's head) — build inside them. Assumed ones — "we always do it this way" — are worth one question, not a declaration: "is that a real limit, or just how it's usually done?" Confirmed real, drop it. Unsure, offer an idea on each side.
- The problem is genuinely narrow — regulated, physically constrained, one correct technical answer. Forcing three angles here is theater. Say so and give the honest, straight read instead.
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.
- yesterday First seen · 69 lines · 23 tokens per session scan A cb7e61aeaaa2
wildcard is an agent published in the GitHub repository block/berd (828 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,796 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.