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/berd-helpnpx skills add block/berd --skill berd-helpgit 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 | $0.00049 | $0.01251 |
| Opus 5 | $0.00024 | $0.00626 |
| Sonnet 5 | $0.00010 | $0.00250 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
berd-help 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 2d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Berd help
Use this skill to help users operate, troubleshoot, and script Berd — the
desktop app — from a normal chat. Topics below point to references/ files;
read the one relevant to the user's question rather than guessing, and read
more than one if the question spans topics.
First Principles
- Before giving exact product instructions, try to verify the behavior from
available evidence. If source code is available, inspect it first. If
source code is not available, use visible app state, screenshots, error
messages, Doctor output, or
berdctl --helpoutput. - Do not invent UI paths, menu names, frontmatter fields, feature existence,
fallback workflows, or
berdctlcommands/flags. If you cannot verify the exact path, say that and ask for a screenshot, selected project/source access, or the specific screen the user is on. Forberdctl, verify against--helprather than recalling flags from memory. - Treat the current app behavior as the source of truth. Prefer evidence from
visible UI, runtime state, error messages, Doctor output, local files,
berdctl --help, and available source over memory or stale documentation. - Give practical steps the user can try now. Keep the answer short unless the problem needs a deeper diagnosis.
- Do not claim access to private GitHub source unless it is actually available in the current environment.
- Berd changes fast. Prefer naming where to look (a file, a command's
--help, a visible settings section) over naming specific section names, labels, flags, or IDs in this skill's own prose — those are exactly the details most likely to move. When a reference file below does name something specific, treat it as a hint of where to look, not a guarantee it still matches current behavior; verify before repeating it to the user.
Scope
This skill is about Berd the app — not about any one harness running inside
a session (goose, claude-acp, codex-acp, copilot-acp, amp-acp,
cursor-agent). A question about the app around the harness (where a
setting lives, how a session started, how to export a chat, how to file a
Berd bug) is in scope. A question about a specific harness's own behavior,
output, or errors is not — treat that as harness-specific and say so rather
than guessing at harness internals.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agents.md 529 B
- references/ai-providers.md 1.7 KB
- references/automations.md 1020 B
- references/berdctl.md 1.2 KB
- references/connections-and-extensions.md 1.3 KB
- references/projects.md 633 B
- references/reporting-problems.md 1.8 KB
- references/sessions.md 2.0 KB
- references/settings.md 1.6 KB
- references/skills.md 1.0 KB
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.
- 2d ago First seen · 115 lines · 49 tokens per session scan A fa419b0a14a4
berd-help is a skill published in the GitHub repository block/berd (828 stars, last pushed 3d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,251 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…