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/jackin-project/jackin-dev/jackin-brainstormnpx skills add jackin-project/jackin-dev --skill jackin-brainstormgit clone --depth 1 https://github.com/jackin-project/jackin-devWrote 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/jackin-project/jackin-dev/jackin-brainstorm)<a href="https://agentmods.dev/skills/jackin-project/jackin-dev/jackin-brainstorm"><img src="https://agentmods.dev/badge/skills/jackin-project/jackin-dev/jackin-brainstorm.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 | $0.00037 | $0.00606 |
| Opus 5 | $0.00018 | $0.00303 |
| Sonnet 5 | $0.00007 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
jackin-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 5d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jackin-brainstorm
Turn an existing roadmap item's intent (and any gathered research) into concrete design decisions, through open back-and-forth with the operator, written incrementally into the item's ## Design section.
Judgment task — describe and decide; do not script it, do not write code, do not break work into tasks (that is plan, deferred).
When to use
- Operator runs
jackin-brainstorm <slug>to design an open roadmap item.
When NOT to use
- Creating the item →
jackin-propose. - Large external/codebase investigation →
jackin-research. - Implementing →
/goal Implement <slug>.md.
Arguments
--research— runjackin-researchfirst if the item looks thin.--resume— continue from the current## Designstate.
Process
- Load context. Read
docs/content/docs/roadmap/<slug>.mdx— Problem, Why It Matters, Design-so-far, Related Files — plus any research already linked. - Discuss freeform. Open back-and-forth: surface alternatives, trade-offs, open questions. Pull in jackin❯ design principles and the relevant rule files (
ENGINEERING.md,HOST_AND_CONTAINER.md, TUI/docs rules) as constraints. Prefer one question at a time; check in as each part settles. - Write incrementally. As each point settles, append or update the matching part of
## Designin the.mdx— the decision plus a one-line why.--resumepicks up from there. - Hit an unknown? Gather quickly (Explore/grep, or
deep-research). Large investigation → spin a separatejackin-researchdossier and link it from## Design. Then resume deciding. - Converge. When
## Designcovers the approach end to end, summarize and point at the implementation step (/goal Implement <slug>.md). - Commit + push.
docs:per settled chunk (push after every commit).
Common mistakes
- Writing code, or filling
## Tasks— out of scope. - Dumping a finished design without the back-and-forth, or asking many questions at once.
- Recording decisions only in chat instead of into
## Design(it must be resumable). - Restating rule-file content instead of referencing it by name.
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.
- 5d ago First seen · 46 lines · 37 tokens per session scan A afda534174a3
jackin-brainstorm is a skill published in the GitHub repository jackin-project/jackin-dev (3 stars, last pushed 4d ago), licensed Apache-2.0. It adds 37 tokens to every session and 606 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.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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.
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…