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 mhylle/claude-skills-collection --skill tt-brainstormgit clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/mhylle/claude-skills-collection/tt-brainstorm)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/tt-brainstorm"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/tt-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/mhylle/claude-skills-collection/tt-brainstorm"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/tt-brainstorm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00197 | $0.03606 |
| Opus 5 | $0.00098 | $0.01803 |
| Sonnet 5 | $0.00039 | $0.00721 |
| Haiku 4.5 | $0.00020 | $0.00361 |
Grade A, and why
tt-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 12d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tt-brainstorm
Tasktracker-native single-session brainstorming. Refines a raw idea through Socratic questioning and targeted analytical frameworks, then persists the refined idea as a brainstorm document tree in tasktracker (not as a file in docs/brainstorms/). Every meaningful decision is recorded as a BrainstormDecision with chosen / deferred / rejected options, so downstream tooling can convert the brainstorm into a real task tree.
The key philosophy: adapt the analysis to the idea, not the idea to the analysis. Different ideas need different frameworks — a risk-heavy initiative wants Premortem, a product feature wants SCAMPER. Pick what generates insight; skip what generates filler.
How this differs from /brainstorm
/brainstorm |
/tt-brainstorm (this skill) |
|
|---|---|---|
| Output | docs/brainstorms/YYYY-MM-DD-*.md file |
Brainstorm tree in tasktracker (no file) |
| Decisions | Free text in markdown | Structured BrainstormDecision rows |
| Handoff to plan | Manual re-reading | promoteBrainstorm → task tree, one call |
| Project context | None | Bound to a tasktracker project |
| Time tracking | None | Auto-heartbeats while active |
If the user is not using tasktracker for this work, use /brainstorm instead. This skill assumes the tasktracker MCP is wired up.
Workflow
Step 0: Establish project context (MANDATORY first step)
Brainstorms in tasktracker live under a project. Before any other work, figure out which project. This is the single most common failure mode of a tasktracker session, so do not skip it.
1. tasktracker_listProjects({search: "<topic-keywords>"})
- Search liberally with the user's own words. Don't trust your memory.
- Inspect candidates with getProject if the name is close-but-not-identical.
2. If no project matches:
- Offer to scaffold one via /init-project (recommended).
- Or, if the user insists on inline scaffolding, call
tasktracker_createProjectFromTemplate with the four template keys
(lifecycle, techStack, deployment, projectType). See workflow guide.
3. If a project exists:
- Find its brainstorm-lifecycle phase task
(metadata.lifecycleSlug = "brainstorm").
- tasktracker_setActiveTask(<phase-1-task-id>).
This starts auto-heartbeating — every subsequent tool call now
contributes to that task's TaskTimeLog.
What ships with it
2 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.
- 12d ago First seen · 276 lines · 197 tokens per session scan A c1a8e3b7440c
tt-brainstorm is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 9d ago), licensed MIT. It adds 197 tokens to every session and 3,606 once invoked, about $0.0010 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.
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…