BITE: Skill for Claude Code

.claude/skills/idea-focus-coach/SKILL.md

idea-focus-coach is a skill for Claude Code from RipeMangoBox/BITE. It costs 52 tokens per session (481 once invoked), scanned A, original, MIT.

A guided research-planning skill that turns a broad idea into a focused, testable plan. TDD here means test-driven development of a research idea through hypotheses and small experiments.

In plain words
What is it for?
Use it to frame a research problem, identify the target user or situation, cut scope, prioritize hypotheses, and design a smallest useful experiment.
Why use it?
It helps narrow an unclear topic, define success, rank possible explanations, and decide what to test first. It is for planning rather than issuing an accept-or-reject review verdict.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is RipeMangoBox/BITE's own configuration. It tells Claude Code how to work on BITE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything BITE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RipeMangoBox/BITE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/RipeMangoBox/BITE/main/.claude/skills/idea-focus-coach/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/RipeMangoBox/BITE

Made for: Claude Code.

Wrote 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.

agentmods badge for idea-focus-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/ripemangobox/bite/idea-focus-coach.svg)](https://agentmods.dev/skills/ripemangobox/bite/idea-focus-coach)
Your own site
<a href="https://agentmods.dev/skills/ripemangobox/bite/idea-focus-coach"><img src="https://agentmods.dev/badge/skills/ripemangobox/bite/idea-focus-coach.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 481 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.00481
Opus 5 $0.00026 $0.00241
Sonnet 5 $0.00010 $0.00096
Haiku 4.5 $0.00005 $0.00048

Measured 6d ago against content hash 525f1c11d125, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

idea-focus-coach 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 6d 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.

.claude/skills/idea-focus-coach/SKILL.md · 68 lines

What it actually says

Idea Focus Coach

Purpose

Turn broad or fuzzy research thoughts into a focused and executable plan.

This is a co-creation and convergence mode. It does not provide accept/reject-style reviewer verdicts.

Positioning

  • Focus: define target, narrow scope, choose hypotheses, set MVP validation.
  • Output style: roadmap-like action plan.

Knowledge protocol

  1. KB-first: start with papers-query-knowledge-base to ground related work and feasible spaces.
  2. On-demand web checks: search web only for uncertainty gaps or fast-moving recent lines.

Step-by-step convergence flow

  1. Problem framing
    • one-sentence problem statement
    • target user/scenario
  2. Success criteria
    • primary metric(s)
    • minimum success threshold
  3. Scope cuts
    • must-have vs out-of-scope
  4. Hypothesis prioritization
    • list candidate hypotheses
    • rank by impact × feasibility
  5. MVP experiment plan
    • smallest meaningful experiment
    • baseline, data, expected signal

Interaction contract

  • Advance with one key decision question at a time when ambiguity exists.
  • Keep each round focused and actionable.
  • End each round with explicit next step.

Output contract

Return structured sections:

  1. Focused problem statement
  2. Prioritized goals and constraints
  3. Out-of-scope list
  4. Top hypotheses and rationale
  5. Next 1-2 experiments (this week)
  6. Risks and stop-loss signals

Boundaries

  • No reviewer verdict language (accept/reject/confidence score).
  • No over-broad brainstorming without convergence checkpoints.

Independence

This skill can be used independently and does not depend on outputs from research-brainstorm-from-kb or reviewer-stress-test. Users can directly bring fuzzy ideas into the focus flow. Likewise, focus output can (but does not have to) be passed to reviewer-stress-test for further challenge.

Changes

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.

  1. 6d ago First seen · 68 lines · 52 tokens per session scan A 525f1c11d125

Subscribe to this mod's changes

idea-focus-coach is a skill published in the GitHub repository RipeMangoBox/BITE (61 stars, last pushed 24d ago), licensed MIT. It adds 52 tokens to every session and 481 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 2026-08-30.

Related

Other skills, from other repositories

results-report

This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict…

Galaxy-Dawn/claude-scholar · 78 tokens

wiki-lint

Audit and maintain the health of the Obsidian wiki. Use this skill when the user wants to check their wiki for issues, find orphaned pages, detect contradictions, identify stale content, fix broken wikilinks, or perform general maintenance on their knowledge base. Also triggers on "clean up the wiki", "what needs…

Ar9av/obsidian-wiki · 152 tokens

wiki-export

Export the Obsidian wiki's knowledge graph to structured formats for use in external tools. Use this skill when the user says "export wiki", "export graph", "export to JSON", "export to Gephi", "export to Neo4j", "export to Postgres", "export to SQL", "graphml", "visualize wiki", "knowledge graph export", "export to…

Ar9av/obsidian-wiki · 172 tokens

agent-identifier

Use when creating or configuring Claude Code agents and their frontmatter.

Galaxy-Dawn/claude-scholar · 17 tokens

code-review-excellence

This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.

Galaxy-Dawn/claude-scholar · 43 tokens

web-design-reviewer

This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage…

Galaxy-Dawn/claude-scholar · 74 tokens