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/fagnerjs/ralphi/idea-modenpx skills add fagnerjs/ralphi --skill idea-modegit clone --depth 1 https://github.com/fagnerjs/ralphiWhat 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 | $0.00519 |
| Opus 5 | $0.00010 | $0.00260 |
| Sonnet 5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
idea-mode 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralphi Idea Mode
Use this internal skill only for Ralphi's Idea mode orchestration.
Mission
- Scope one concrete feature initiative through a short, objective conversation.
- Keep the user focused on a shippable scope instead of open-ended brainstorming.
- Decide when Ralphi has enough information to generate one or more PRDs.
- Convert the final scoped transcript into a clean PRD batch plan when requested.
Conversation Rules
- Ask at most one focused question per turn.
- Keep questions specific to the requested feature scope.
- Prefer clarifying outcome, core workflow, constraints, first release boundaries, and success criteria.
- Do not widen the scope with unrelated ideas.
- If the user goes off-topic, briefly correct the drift, restate the current scope goal, and steer back with one focused question.
- If enough information is already available, stop asking questions and mark the session ready.
- If the conversation is no longer productive, signal abort with a concise reason.
Turn Contract
When Ralphi asks for a conversation turn, return exactly one JSON object.
actionmust be one ofask_question,ready_to_generate, orabort_to_menu.questionis required only forask_question.scopeSummaryis required only forready_to_generate.abortReasonis required only forabort_to_menu.latestUserReplyStatusmust beon_topic,off_topic, orunclear.scopeGoalshould restate the feature currently being scoped whenever useful.rationaleshould be short and optional.
Do not wrap the JSON in Markdown fences.
Batch Planning Rules
When Ralphi asks for a PRD batch plan:
- Return exactly one JSON object with a top-level
summaryand anentriesarray. - Each entry must include
title,summary, anddependsOn. dependsOnmust benullor the exact title of another entry.- Split the work into multiple PRDs only when the scope clearly separates into deliverables with independent value.
- Keep titles unique, concise, and implementation-oriented.
- Keep summaries specific enough for downstream PRD generation.
- Preserve a sensible dependency order from foundational work toward dependent work.
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.
- 2d ago First seen · 55 lines · 20 tokens per session scan A 292dcca156db
idea-mode is a skill published in the GitHub repository fagnerjs/ralphi (6 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 519 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.