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/sponge-b0b/polaris/prototypenpx skills add sponge-b0b/Polaris --skill prototypegit clone --depth 1 https://github.com/sponge-b0b/PolarisWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sponge-b0b/polaris/prototype)<a href="https://agentmods.dev/skills/sponge-b0b/polaris/prototype"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/prototype.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00020 | $0.00822 |
| Opus 5 | $0.00010 | $0.00411 |
| Sonnet 5 | $0.00004 | $0.00164 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
prototype 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype
A prototype is throwaway code that answers a question. The question decides the shape.
Pick a branch
Identify which question is being answered:
- "Does this logic / state model feel right?" →
LOGIC.md. Build a tiny interactive terminal app that pushes the state machine through cases that are hard to reason about on paper. - "What should this look like?" →
UI.md. Generate several meaningfully different UI variations on a single route using the project's existing routing conventions.
If the question is genuinely ambiguous and cannot be resolved from context, ask. Otherwise choose the branch that best matches the surrounding work and state the assumption.
Before building, if the Living Entity Wiki exists, use wiki/index.md to read the relevant entity's Rejected Approaches. If the same approach was already rejected, do not silently retry it. Surface the prior reasoning; re-prototype only when circumstances have materially changed or a Reconsider when: condition may now apply.
Rules
- Throwaway from day one. Keep the prototype close to the code it explores, but name it clearly as a prototype.
- One command to run. Use the project's existing tooling; do not introduce a new runner.
- No persistence by default. Use memory unless persistence itself is the question. Any scratch persistence must be isolated and disposable.
- Skip production polish. No abstractions, broad test suite, production observability, or generalized error handling beyond what is needed to answer the question reliably.
- Surface the state. After each logic action or UI variant switch, expose the relevant resulting state.
- Test only the question. Do not mistake incidental prototype choices—single-file structure, no DI, in-memory storage, etc.—for validated production architecture.
Verdict
Classify the result as:
- Validated — the tested idea is worth carrying forward.
- Invalidated — the experiment produced concrete evidence against the approach.
- Inconclusive — the experiment did not answer the question reliably.
What ships with it
3 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.
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.
- 3d ago First seen · 87 lines · 20 tokens per session scan A 734f5c8d4aca
prototype is a skill published in the GitHub repository sponge-b0b/Polaris (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 20 tokens to every session and 822 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 2026-08-31.
Other skills, from other repositories
nornweave-api
Give AI agents their own email inboxes using the NornWeave API. Use when building email agents, sending/receiving emails programmatically, managing inboxes, retrieving threads, searching messages, or integrating with email providers (Mailgun, SES, SendGrid, Resend). NornWeave provides LLM-ready markdown parsing and…
commit-push
Commit and push the changes made on this chat session to the current branch. Use best practices from Conventional Commits.
commit
Commit the changes made on this chat session to the current branch. Use best practices from Conventional Commits.
hybrid-ralph
Hybrid architecture combining Ralph's PRD format with Planning-with-Files' structured approach. Auto-generates PRDs from task descriptions, manages parallel story execution with dependency resolution, and provides context-filtered agents for efficient multi-story development.
mega-plan
Project-level multi-task orchestration system. Manages multiple hybrid:worktree features in parallel with dependency resolution, coordinated PRD generation, and unified merge workflow.
planning-with-files
Implements Manus-style file-based planning for complex tasks. Creates taskplan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear and optional Git worktree mode.