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/lfyxhappy/lfcode/brainstormnpx skills add lfyxhappy/lfcode --skill brainstormgit clone --depth 1 https://github.com/lfyxhappy/lfcodeWhat 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 | $0.00038 | $0.02979 |
| Opus 5 | $0.00019 | $0.01489 |
| Sonnet 5 | $0.00008 | $0.00596 |
| Haiku 4.5 | $0.00004 | $0.00298 |
Grade A, and why
compose: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 yesterday.
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.
This is a copy
73% identical to brainstorming — 115 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming Ideas Into Designs
Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.
Autonomous override: When no user is available to approve, this HARD-GATE does not apply: skip design presentation and approval, proceed directly to implementation, treating every approval gate as auto-approved.
Anti-Pattern: "This Is Too Simple To Need A Design"
Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.
Autonomous override: When no user is available, skip this anti-pattern guidance — proceed directly to exploring context and implementing; do not present a design for approval.
Checklist
You MUST create a task for each of these items and complete them in order:
Autonomous mode (no user available): Skip steps 2–8. Only do: explore project context (step 1) → implement directly (invoke compose:plan or compose:execute). Do NOT present a design, ask questions, write a spec, or wait for approval.
- Explore project context — check files, docs, recent commits
- Offer visual companion (if topic will involve visual questions) — this is its own message, not combined with a clarifying question. See the Visual Companion section below.
- Ask clarifying questions — one at a time, understand purpose/constraints/success criteria
- Propose 2-3 approaches — with trade-offs and your recommendation
- Present design — in sections scaled to their complexity, get user approval after each section
- Write design doc (optional, multi-step features only) — save to
docs/compose/specs/YYYY-MM-DD-<topic>-design.mdand commit. For single-step fixes or small changes, keep the design in conversation context only. - Spec self-review (if doc written) — quick inline check for placeholders, contradictions, ambiguity, scope (see below)
- User reviews written spec (if doc written) — ask user to review the spec file before proceeding
- Transition to implementation — invoke compose:plan to create implementation plan
What ships with it
7 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.
- yesterday First seen · 221 lines · 38 tokens per session scan A 2760b0916cfd
compose:brainstorm is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,979 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 73% identical to brainstorming, differing in 115 lines, and is treated as a copy.
Other skills, from other repositories
Review a GitHub PR (via gh)
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Implement (multi-agent loop)
Orchestrate an implement -> review -> fix loop with subagents until reviewers sign off.
Best of N (parallel attempts)
Delegate N parallel subagents on the same task, then pick the best result.
Check work (verify against criteria)
Verify an implementation against acceptance criteria with a reviewer and a tester.
Commit (clean, conventional)
Stage the right changes and write a clear, conventional commit message.
Design doc (write -> review loop)
Draft a design document and iterate writer/reviewer subagents until consensus.