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 skills add navapbc/rebar --skill rebar-brainstormgit clone --depth 1 https://github.com/navapbc/rebarWrote 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/navapbc/rebar/rebar-brainstorm)<a href="https://agentmods.dev/skills/navapbc/rebar/rebar-brainstorm"><img src="https://agentmods.dev/badge/skills/navapbc/rebar/rebar-brainstorm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/navapbc/rebar/rebar-brainstorm"><img src="https://agentmods.dev/badge/skills/navapbc/rebar/rebar-brainstorm.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00069 | $0.02563 |
| Opus 5 | $0.00034 | $0.01282 |
| Sonnet 5 | $0.00014 | $0.00513 |
| Haiku 4.5 | $0.00007 | $0.00256 |
Grade A, and why
rebar-brainstorm 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 11d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm Protocol
A structured clarification loop for designing something (an agent, skill, tool, feature, or system) before any implementation begins. The goal is a design that is ready to implement: intent is clear, edge cases are settled, and every decision the build depends on has been made — not to start building.
Core loop
Ask questions one at a time until you fully understand, for each thing being designed:
- Purpose — what it does and why it exists.
- Problem it solves — the concrete pain point, with examples.
- Edge cases — how it should behave when inputs are ambiguous, missing, conflicting, or unusual.
- Implementation — exactly how you would build it, with high confidence.
Do not move on to implementation until all four are clear for every item in scope.
How to ask
- One question per turn. Pick the single highest-leverage unknown and ask only that. Never send more than one question in a message.
- Ask only what the user alone can answer. Reserve questions for intent, priorities, preferences, and tradeoff calls — the things only the user knows. Everything factual, discover yourself first from the codebase, docs, git history, and prior art. Never ask the user for something you can find on your own.
- Ask only what's genuinely unresolved. Treat everything the user has already told you — directly or in passing — as settled, and build on it. Never re-ask something already answered.
- Be critical. Challenge the user's assumptions. If a premise seems flawed, redundant with existing tooling, or likely to fail in practice, say so directly and explain why — before asking the next question.
- Ground every question and suggestion. Each substantive question or design suggestion should be backed by at least one of:
- Web research — published research, official docs, blog posts from credible practitioners.
- Prior art — GitHub repos, existing tools, established patterns that solve similar problems.
- Subagent convergence — independent subagent review that agrees with (or sharpened) the reasoning.
- Briefly cite or summarize the grounding when presenting a question or challenge, so the user can evaluate it.
What ships with it
1 file 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.
- 11d ago First seen · 157 lines · 69 tokens per session scan A ae180bc79cdb
rebar-brainstorm is a skill published in the GitHub repository navapbc/rebar (4 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 2,563 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…