agentmods.dev

Forge-Agentic-Coding-CLI: Skill for Claude Code

.claude/skills/idea-wizard/SKILL.md

idea-wizard is a skill for Claude Code from hoangsonww/Forge-Agentic-Coding-CLI. It costs 37 tokens per session (400 once invoked), scanned A, original, MIT.

A guided brainstorming process for adding features to an existing Forge codebase. It creates 30 ideas, narrows them to 5, expands the shortlist to 15, and waits for a person to choose what to pursue.

In plain words
What is it for?
It is for planning features in a mature project, checking ideas against existing work, creating detailed beads—small tracked work items—and polishing them for implementation.
Why use it?
It helps teams avoid weak or duplicate feature ideas and checks each surviving idea against the current project work and security rules.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is hoangsonww/Forge-Agentic-Coding-CLI's own configuration. It tells Claude Code how to work on Forge-Agentic-Coding-CLI 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 Forge-Agentic-Coding-CLI configures →

not rated 26repo 1mo ago A scan 37 tokens original MIT
View source ↗ hoangsonww/Forge-Agentic-Coding-CLI hoangsonww.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/Forge-Agentic-Coding-CLI. 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/hoangsonww/Forge-Agentic-Coding-CLI/master/.claude/skills/idea-wizard/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/Forge-Agentic-Coding-CLI

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-wizard

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangsonww/forge-agentic-coding-cli/idea-wizard/github.svg)](https://agentmods.dev/skills/hoangsonww/forge-agentic-coding-cli/idea-wizard)
Your own site
<a href="https://agentmods.dev/skills/hoangsonww/forge-agentic-coding-cli/idea-wizard"><img src="https://agentmods.dev/badge/skills/hoangsonww/forge-agentic-coding-cli/idea-wizard/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.

agentmods 80×15 button for idea-wizard

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangsonww/forge-agentic-coding-cli/idea-wizard"><img src="https://agentmods.dev/badge/skills/hoangsonww/forge-agentic-coding-cli/idea-wizard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 400 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00037 $0.00400
Opus 5.5 $0.00015 $0.00160
Sonnet 5.5 $0.00007 $0.00080
Haiku 4.5 $0.00004 $0.00040

Measured 2mo ago against content hash 0d9833236706, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

idea-wizard 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 2mo 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-wizard/SKILL.md · 40 lines

What it actually says

/idea-wizard — add features to existing Forge

Winnowing forces critical evaluation. Asking for "5 ideas" directly produces weak lists; asking for 30 then winnowing produces strong ones.

Phases

  1. Ground in reality. Read AGENTS.md + CLAUDE.md. Skim the open bead graph: jq -c 'select(.status!="closed")' .beads/beads.jsonl.
  2. Generate 30, winnow to 5. Use the Phase 2 prompt in .flywheel/prompts/idea-wizard.md.
  3. Expand to 15. "OK and your next best 10 and why." Each one must be verified novel against the current bead graph.
  4. Human review. You pick from the 15 which to pursue.
  5. Create beads in .beads/beads.jsonl with full descriptions.
  6. Polish 4–5 times with /polish-beads.

When NOT to use this

  • For bounded, small changes — use the TODO-list approach inline instead, without formal beads.
  • For greenfield projects — use /plan from the start.
  • For porting ideas from an external project — use the research-and-reimagine approach (see FLYWHEEL.md §5); save the proposal to .flywheel/proposals/.

Verification before bead creation

For every idea that survives winnowing, verify:

  • It respects Forge's security and permission invariants.
  • It fits under one of the existing subsystem labels.
  • It doesn't duplicate something closed (check closed beads too).
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. 2mo ago First seen · 40 lines · 37 tokens per session scan A 0d9833236706

Subscribe to this mod's changes

idea-wizard is a skill published in the GitHub repository hoangsonww/Forge-Agentic-Coding-CLI (26 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 400 once invoked, about $0.0001 per session on Opus 5.5. 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.

Planningagentic-aiagentic-codingagentic-workflowagentsclicommand-line-interface
Related

idea-wizard compared with skills from other repositories

idea-wizard next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
idea-wizardhoangsonww/Forge-Agentic-Coding-CLISkill261mo agoMITA37Claude Code
code-revieweralirezarezvani/claude-code-tresorSkill7824mo agoMITA54Claude Code
git-commit-helperalirezarezvani/claude-code-tresorSkill7824mo agoMITA55Claude Code
test-generatoralirezarezvani/claude-code-tresorSkill7824mo agoMITA55Claude Code
readme-updateralirezarezvani/claude-code-tresorSkill7824mo agoMITA49Claude Code
api-documenteralirezarezvani/claude-code-tresorSkill7824mo agoMITA48Claude Code
dependency-auditoralirezarezvani/claude-code-tresorSkill7824mo agoMITA51Claude Code