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 skills/block/berd/agent-buildernpx skills add block/berd --skill agent-buildergit 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 | $0.00039 | $0.00567 |
| Opus 5 | $0.00019 | $0.00283 |
| Sonnet 5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
agent-builder 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Builder
Use this skill when managing Berd agents/personas in Agent Markdown format.
Storage
Agents are UTF-8 Markdown files with YAML frontmatter:
- Global:
~/.agents/agents/<slug>.md - Project-local:
<project>/.agents/agents/<slug>.md
Default to global unless the user asks for project-local. Use platform path APIs or shell-safe home expansion.
Format
Each agent is one .md file:
---
name: Agent Name
description: A concise summary of what this agent does
provider: optional-provider
model: optional-model
avatar: optional-avatar
---
Agent instructions here.
Required frontmatter keys are name and description. The description must be a trimmed, non-empty summary of what the agent does; never create or save an agent with a missing, blank, or placeholder description. If the user has not supplied enough context to write an accurate description, ask for one before saving. Preserve all other frontmatter keys when editing existing agents unless the user explicitly changes them. The Markdown body is the agent’s system prompt/persona instructions.
When writing or generating a description or body, do not assign the agent a gender or gendered pronouns unless the user asked for one. Use it/its or they/them for the agent, matching how it is framed (tool vs. character), or avoid pronouns; people the instructions describe get they/them. Preserve pronouns the user chose, in either direction.
Names and Slugs
For create/rename, require a trimmed name that is non-empty, ≤80 characters, and contains no / or \.
Derive <slug> from the name by lowercasing, replacing each non-ASCII alphanumeric run with -, collapsing/trimming -, truncating to 64 characters, and falling back to agent.
Write <slug>.md; on create collisions, use <slug>-2.md, <slug>-3.md, etc.
Workflow
When editing, read the existing file first. Resolve targets by exact path, frontmatter name, then slug filename. Ask only if multiple matches remain.
Prefer direct file edits over helper scripts. Do not require Python, Node, or another runtime unless the current repo already requires it.
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 · 56 lines · 39 tokens per session scan A e576c7a5b6b4
agent-builder is a skill published in the GitHub repository block/berd (828 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 567 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…