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/skill-buildernpx skills add block/berd --skill skill-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 | $0.00061 | $0.01038 |
| Opus 5 | $0.00030 | $0.00519 |
| Sonnet 5 | $0.00012 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
skill-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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Builder
Use this skill when creating, editing, or inspecting Berd skills.
What a Skill Is
A skill is a folder with a required SKILL.md file and optional supporting
resources:
skill-name/
├── SKILL.md
├── scripts/
├── references/
└── assets/
Do not create README.md, CHANGELOG.md, or extra documentation files inside a
skill folder. Skill documentation belongs in SKILL.md or references/.
Storage Decision
Skills can be global or project-local:
- Global:
~/.agents/skills/<skill-name>/SKILL.md - Project-local:
<project>/.agents/skills/<skill-name>/SKILL.md
Default to global unless the user is clearly working in a project directory.
If a project directory is active and the user has not specified scope, ask whether the skill should be saved for this project only or globally for all projects.
Do not ask when intent is clear:
- Project-local: "this repo", "this project", "only here", "project skill"
- Global: "all projects", "global", "personal skill", "always available"
When editing an existing skill, keep it in its current location unless the user explicitly asks to move it.
Format
SKILL.md is UTF-8 Markdown with YAML frontmatter:
---
name: skill-name
description: What the skill does. Use when the user asks to...
---
# Skill Title
Instructions the agent follows.
Required frontmatter keys are name and description. Preserve unknown
frontmatter keys when editing existing skills unless the user explicitly asks to
change them.
The description is the trigger surface. It must explain both what the skill
does and when to use it. Include concrete user phrases or task types. Keep it
specific enough to avoid triggering for unrelated work.
Names
Skill names and folder names must match.
Use lowercase kebab-case:
- Allowed:
a-z,0-9, and- - Maximum: 64 characters
- Do not start or end with
- - Do not use spaces, underscores, slashes, or capitals
Normalize user-provided titles by lowercasing, replacing invalid character runs
with -, collapsing repeated separators when practical, trimming leading and
trailing -, and truncating to 64 characters. Fall back to skill if needed.
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 · 142 lines · 61 tokens per session scan A 8fc80e9306fe
skill-builder is a skill published in the GitHub repository block/berd (828 stars, last pushed 2d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,038 once invoked, about $0.0003 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…