seed

A guide for trying unfamiliar technology in a controlled way. It focuses on understanding the possible damage of an experiment and keeping that damage contained.

In plain words
What is it for?
Use it when prototyping, testing new dependencies or databases, exploring AI or machine-learning integrations, or working near production.
Why use it?
It reduces the chance that a prototype, new database, library, or AI integration will affect important data or production systems.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/itsbroken-ai/forge-plugin/seed
Any agent
npx skills add itsbroken-ai/forge-plugin --skill seed
Clone the repo
git clone --depth 1 https://github.com/itsbroken-ai/forge-plugin

Made for: Claude Code, Codex.

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,799 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00106 $0.02799
Opus 5 $0.00053 $0.01399
Sonnet 5 $0.00021 $0.00560
Haiku 4.5 $0.00011 $0.00280

Measured 2d ago against content hash 8632e85c89c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seed 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.

skills/seed/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

forge:seed — Safe Ethical Experimentation and Development

You want to try something. Good. That instinct is how good software gets built.

This skill exists to make sure your experiments teach you something instead of waking you up at 3am. The philosophy is simple: push boundaries, but know where the walls are before you start swinging.

SEED is not a gate. It is a guide. The answer is almost never "don't do that." The answer is "do that, and here's how to keep it from catching fire."

The SEED Principles

Safe

Every experiment should have a blast radius you can contain. If the worst case is "I restart my dev server," go wild. If the worst case is "production database gets wiped," you need a sandbox first.

Containment is not about fear. It is about knowing what breaks and how far the break travels. A controlled explosion is science. An uncontrolled explosion is a resume-generating event.

Ask yourself: "If this goes completely sideways, what is the worst thing that happens?" If you can live with the answer, proceed. If you cannot, shrink the blast radius until you can.

Ethical

Every system you build will eventually be used by someone who is not you, in a way you did not expect. That is not paranoia, it is software development.

"Could this be misused?" is always a valid question. Not because you need to prevent every possible abuse before writing line one, but because thinking about it early costs nothing and thinking about it after an incident costs everything.

This is not about being heavy-handed. It is about being thoughtful. Consider the humans downstream of your code: the users, the data subjects, the ops team who will be paged when something breaks.

Experimentation

Push boundaries. Try things. Break things in controlled environments. The goal is learning, not perfection.

The developer who never experiments ships stale code. The developer who experiments without guardrails ships broken code. You want to be the developer who experiments with intention: clear hypothesis, contained environment, observable results.

Read the full file on GitHub · 217 lines

Changes

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.

  1. 2d ago First seen · 217 lines · 106 tokens per session scan A 8632e85c89c0

Subscribe to this mod's changes

seed is a skill published in the GitHub repository itsbroken-ai/forge-plugin (11 stars, last pushed 5mo ago), licensed MIT. It adds 106 tokens to every session and 2,799 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens